Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
e0c1b37c0b | ||
|
|
b004fcd644 | ||
|
|
0c7fe15635 | ||
|
|
2be3b32586 | ||
|
|
867132f26b | ||
|
|
4522b8fa40 | ||
|
|
2d221f6204 | ||
|
|
626dc1df8f | ||
|
|
02396f4482 | ||
|
|
7724290921 | ||
|
|
3b1804b093 | ||
|
|
4cd8dbfc73 | ||
|
|
dc4bdf6efc | ||
|
|
a458bded09 |
+47
-14
@@ -38,6 +38,9 @@ Each `Get` record (one per served document):
|
|||||||
(`x-pagerite-preload` header): never counted as a view, crawler hit or
|
(`x-pagerite-preload` header): never counted as a view, crawler hit or
|
||||||
abuse — recorded only so a navigation later served from the in-memory page
|
abuse — recorded only so a navigation later served from the in-memory page
|
||||||
cache (which issues no GET at all) can be attributed this GET's status,
|
cache (which issues no GET at all) can be attributed this GET's status,
|
||||||
|
- `lang` — rendered content language of the served document (the resolved
|
||||||
|
language of a localized page), `""` for non-localized responses (404
|
||||||
|
probes, reserved paths),
|
||||||
- `client` — 6-byte blake3 hash referencing `Analytics.clients`.
|
- `client` — 6-byte blake3 hash referencing `Analytics.clients`.
|
||||||
|
|
||||||
304 revalidation responses return before recording and are not logged.
|
304 revalidation responses return before recording and are not logged.
|
||||||
@@ -51,7 +54,9 @@ Each `Msg` record (one per pagerite.js activity message over `/_ws`):
|
|||||||
- `to` — navigation target (validated at record time: internal slug path or
|
- `to` — navigation target (validated at record time: internal slug path or
|
||||||
external https URL; anything else is dropped — sanitation, not
|
external https URL; anything else is dropped — sanitation, not
|
||||||
classification),
|
classification),
|
||||||
- `read` — active seconds spent on `fr` since the previous report.
|
- `read` — active seconds spent on `fr` since the previous report,
|
||||||
|
- `lang` — rendered language reported by the client for the page the
|
||||||
|
activity happened on (the page's `<html lang>`; `""` from old clients).
|
||||||
|
|
||||||
Each `Client` record (shared by every event, keyed by hash):
|
Each `Client` record (shared by every event, keyed by hash):
|
||||||
|
|
||||||
@@ -104,7 +109,11 @@ The client (`pagerite.js`) keeps a WebSocket connection to `/_ws` for the
|
|||||||
whole browsing session and sends activity messages over it — JSON text
|
whole browsing session and sends activity messages over it — JSON text
|
||||||
frames matching the server's `Ping` msgspec struct with the fields `fr`
|
frames matching the server's `Ping` msgspec struct with the fields `fr`
|
||||||
(source path), `to` (navigation target), `read` (active seconds on `fr`
|
(source path), `to` (navigation target), `read` (active seconds on `fr`
|
||||||
since the last report) and `hide`; falsy fields are omitted. One channel
|
since the last report), `lang` (the rendered language of the page the
|
||||||
|
activity happened on — its `<html lang>`, except the language-switch
|
||||||
|
navigation ping, which passes the picked tag explicitly because the view
|
||||||
|
transition applies the new `<html lang>` only after the ping goes out) and
|
||||||
|
`hide`; falsy fields are omitted. One channel
|
||||||
follows the session, so the activity of a visit stays tied together, and
|
follows the session, so the activity of a visit stays tied together, and
|
||||||
while the user is active the accumulated reading time is flushed every few
|
while the user is active the accumulated reading time is flushed every few
|
||||||
seconds: the times are incremental, so a disconnection simply leaves the
|
seconds: the times are incremental, so a disconnection simply leaves the
|
||||||
@@ -173,10 +182,16 @@ for misses.
|
|||||||
(`_SESSION_GAP`). A fresh page load with an already-open visit (second
|
(`_SESSION_GAP`). A fresh page load with an already-open visit (second
|
||||||
tab) extends it, logging a `(direct)` transition. The visit's trail holds
|
tab) extends it, logging a `(direct)` transition. The visit's trail holds
|
||||||
first-seen targets in order; `read` updates accumulate active seconds on
|
first-seen targets in order; `read` updates accumulate active seconds on
|
||||||
the trail item matching `fr`. Each trail item's HTTP status comes from
|
the trail item matching `fr` (preferring the item whose language matches
|
||||||
|
the report, so seconds after a language switch land on the new-language
|
||||||
|
step). Each trail item's HTTP status comes from
|
||||||
the client's latest GET for that path — preloads included, which is what
|
the client's latest GET for that path — preloads included, which is what
|
||||||
allows 404 pages to render red in the viewer even when the navigation
|
allows 404 pages to render red in the viewer even when the navigation
|
||||||
itself was served from the page cache. The entry page's referer and
|
itself was served from the page cache. Each trail item also carries the
|
||||||
|
rendered language: the client's report, for the entry page falling back
|
||||||
|
to its GET's rendered language (old clients don't send one); a page
|
||||||
|
re-visited in a different language becomes a distinct trail step instead
|
||||||
|
of merging into the existing item. The entry page's referer and
|
||||||
`utm_*` tags come from the GET that loaded it (within 10 s before the
|
`utm_*` tags come from the GET that loaded it (within 10 s before the
|
||||||
first message).
|
first message).
|
||||||
- **Crawler hits**: a document GET no activity message matched within
|
- **Crawler hits**: a document GET no activity message matched within
|
||||||
@@ -232,6 +247,10 @@ to tell misses from real pages at a glance.
|
|||||||
The `Display` payload contains the derived `visits`, `crawlers` and `abuse`
|
The `Display` payload contains the derived `visits`, `crawlers` and `abuse`
|
||||||
rows (structs `Visit`/`Nav`/`TrailItem`, `CrawlerHit`, `AbuseHit` — display
|
rows (structs `Visit`/`Nav`/`TrailItem`, `CrawlerHit`, `AbuseHit` — display
|
||||||
DTOs only, never persisted), the visible `clients`, the fetched `favicons`,
|
DTOs only, never persisted), the visible `clients`, the fetched `favicons`,
|
||||||
|
the site language context (`multilingual` — translation languages are
|
||||||
|
configured, so the viewer can suppress language UI on single-language
|
||||||
|
sites — and `primary_lang` — the front page's primary language, so the
|
||||||
|
viewer can skip the primary-language default case),
|
||||||
and the aggregates below.
|
and the aggregates below.
|
||||||
|
|
||||||
Each derived `Visit`:
|
Each derived `Visit`:
|
||||||
@@ -243,8 +262,9 @@ Each derived `Visit`:
|
|||||||
- `trail` — the entry page and everything seen afterwards, keyed by the
|
- `trail` — the entry page and everything seen afterwards, keyed by the
|
||||||
timestamp of first sight (insertion order = first-seen order). Each item
|
timestamp of first sight (insertion order = first-seen order). Each item
|
||||||
holds `to` (page path or external exit URL), the accumulated active
|
holds `to` (page path or external exit URL), the accumulated active
|
||||||
reading time in seconds (`read`) and the most recent HTTP status seen
|
reading time in seconds (`read`), the most recent HTTP status seen
|
||||||
for the target (`status`),
|
for the target (`status`) and the rendered language (`lang`; a page
|
||||||
|
seen in two languages within one visit gets one item per language),
|
||||||
- `navs` — every navigation (`fr`, `to`), keyed by its timestamp, repeats
|
- `navs` — every navigation (`fr`, `to`), keyed by its timestamp, repeats
|
||||||
included. The aggregates are computed from this log,
|
included. The aggregates are computed from this log,
|
||||||
- `utm` — `utm_*` query parameters from the landing URL, as a dict.
|
- `utm` — `utm_*` query parameters from the landing URL, as a dict.
|
||||||
@@ -257,7 +277,8 @@ Each derived `CrawlerHit`:
|
|||||||
- `referer` — external https origin of the request, `""` for direct/none,
|
- `referer` — external https origin of the request, `""` for direct/none,
|
||||||
- `query` — raw query string of the request,
|
- `query` — raw query string of the request,
|
||||||
- `status` — HTTP status of the served response (200 for a real page, 404
|
- `status` — HTTP status of the served response (200 for a real page, 404
|
||||||
for a category placeholder or missing page).
|
for a category placeholder or missing page),
|
||||||
|
- `lang` — rendered content language of the served document (from the GET).
|
||||||
|
|
||||||
Each derived `AbuseHit`:
|
Each derived `AbuseHit`:
|
||||||
|
|
||||||
@@ -343,13 +364,25 @@ Axes always start at 0 and end at a multiple of a 1-2-5 major step (max 5
|
|||||||
labeled intervals, minor lines at fifths when integral; the minimum y-axis
|
labeled intervals, minor lines at fifths when integral; the minimum y-axis
|
||||||
range is 10 so tiny values such as a single visit are not stretched to a
|
range is 10 so tiny values such as a single visit are not stretched to a
|
||||||
fractional scale).
|
fractional scale).
|
||||||
The week range is aligned to Monday 00:00 UTC and overlays up to 8 previous
|
The week range is aligned to Monday 00:00 UTC (the current week keeps the
|
||||||
weeks in the muted color at decreasing opacity (the current week keeps the
|
accent color and is truncated at the current bucket, never drawing fake
|
||||||
accent color and is
|
zeroes for the future). Both the week and day views overlay a **"typical"
|
||||||
truncated at the current bucket, never drawing fake zeroes for the future);
|
history curve** in the muted color (`analytics/seasonal.js`, a port of
|
||||||
a compact legend inside the top right of the visits chart marks the current
|
`seasonal.py`): the whole recorded history is densified to 5-minute bins,
|
||||||
ISO week in accent and the overlaid past weeks as "Week M" or "Week M–N" on
|
smoothed with the same Gaussian as the week view, then folded onto a weekly
|
||||||
a muted specimen. Its x labels are weekday names centered at midday UTC, without
|
grid with exponential decay over age — a 7-day half-life for the average
|
||||||
|
time-of-day pattern and a 42-day half-life for per-weekday deviations from
|
||||||
|
it, the deviation shrunk by the effective number of weeks behind each bin
|
||||||
|
(`n_eff / (n_eff + 3)`) so the estimate falls back to the common daily
|
||||||
|
pattern when history is short. History is capped at the most recent 180
|
||||||
|
days, beyond which even the slow kernel's weight is negligible (~5%). The
|
||||||
|
week view draws the full Monday-first
|
||||||
|
estimate as "Typical week" (future included); the day view cuts the rolling
|
||||||
|
24-hour window's bins from the same estimate and labels them by the weekday
|
||||||
|
("Typical Saturday"). A compact legend inside the top right of the visits
|
||||||
|
chart marks the current data in accent (ISO week label, or a bar specimen
|
||||||
|
for "Last 24 hours") and the typical curve on a muted specimen. The week
|
||||||
|
view's x labels are weekday names centered at midday UTC, without
|
||||||
vertical grid
|
vertical grid
|
||||||
lines (day boundaries would be misleading in the viewer's timezone). The
|
lines (day boundaries would be misleading in the viewer's timezone). The
|
||||||
month view labels days the same lineless way — day numbers at noon UTC,
|
month view labels days the same lineless way — day numbers at noon UTC,
|
||||||
|
|||||||
+1
-1
@@ -26,7 +26,7 @@ msgspec Structs for the kanta database. See `docs/content-model.md` for the full
|
|||||||
|
|
||||||
## `markdown.py`
|
## `markdown.py`
|
||||||
|
|
||||||
markdown-it-py renderer (html passthrough + attrs, footnote, deflist, tasklists, admon, gfm_autolink, sub/superscript plugins; typographer + breaks on). In bodies with at least three top-level h1/h2 headings (nested ones, e.g. inside `::: aside`, never participate), each gets a slug id (`python-slugify`, mirroring the editor's `slugify.js` — unicode folds to ASCII, separators become single hyphens) unless the author set `{#id}`, and their text is wrapped in a self-link (`a.anchor`) so section links are copyable; anchored headings also carry `data-line` with their markdown source line (the page editor's section pens and piecewise scroll sync key off it); the first in-body h1 is the article title — when the markdown has no h1, `render(title=...)` injects it as `# {title}` so implicit and explicit titles take the same path — it gets no id and doesn't count toward the three, its self-link is `href=""` (scroll to top); shorter articles stay anchor-free, h3+ is never navigable, and duplicates get `-2`/`-3` suffixes. Custom image rule: relative srcs resolve against the page path; an image standing alone in its paragraph becomes a figure (captioned when titled), while inline-with-text images and raw `<img>` HTML stay plain. A `{dates}` line expands to the article's published/updated dateline (`p.dateline`, from `Node.created`/`modified`; left literal in previews of unsaved pages). Code fences take pandoc-style brace attributes on the info line (` ```{.python .wide #id key=val} ` — the first class is the language when no bare language word precedes the braces) as well as a trailing `{...}` line; both land on the `<pre>`, the `<code>` keeps only the language class.
|
markdown-it-py renderer (html passthrough + attrs, footnote, deflist, tasklists, admon, gfm_autolink, sub/superscript plugins; typographer + breaks on). In bodies with at least three top-level h1/h2 headings (nested ones, e.g. inside `::: aside`, never participate), each gets a slug id (`python-slugify`, mirroring the editor's `slugify.js` — unicode folds to ASCII, separators become single hyphens) unless the author set `{#id}`, and their text is wrapped in a self-link (`a.anchor`) so section links are copyable; anchored headings also carry `data-line` with their markdown source line (the page editor's section pens and piecewise scroll sync key off it); the first in-body h1 is the article title — when the markdown has no h1, `render(title=...)` injects it as `# {title}` so implicit and explicit titles take the same path — it gets no id and doesn't count toward the three, its self-link is `href=""` (scroll to top); shorter articles stay anchor-free, h3+ is never navigable, and duplicates get `-2`/`-3` suffixes. Custom image rule: relative srcs resolve against the page path; an image standing alone in its paragraph becomes a figure (captioned when titled), while inline-with-text images and raw `<img>` HTML stay plain. A lone `{name}` / `{name: args}` line is a block directive: a core rule turns it into a `directive` token (render instance only — the verbatim parser keeps the plain paragraph so segments/chunks see the placeholder source), and the render rule delegates to the resolvers passed as `render(directives=...)`, leaving the source literal where no resolver applies (e.g. the editor preview of a page that does not exist yet). Built in: `{dates}` expands to the article's published/updated dateline (`p.dateline`, from `Node.created`/`modified`, registered by `render()` when `created` is given); views.py resolves `{cards}` — the page's published children, one card each (on the front page: the other top-level pages) — and `{cards: path path/* path/** ...}` (space-separated: a plain path renders that page alone, `path/*` its published children, `path/**` all published descendant pages; a page-less item is represented by its first leaf page, the nav-link logic) into the same card-row markup as category pages (`.cards.wide`, a boundary block outside the column segments). A page with any `{cards}` tag drops the automatic end-of-page child cards; multiple tags each render their own row. Code fences take pandoc-style brace attributes on the info line (` ```{.python .wide #id key=val} ` — the first class is the language when no bare language word precedes the braces) as well as a trailing `{...}` line; both land on the `<pre>`, the `<code>` keeps only the language class.
|
||||||
|
|
||||||
`render()` returns a `Rendered(html, multicol)`: the article content segmented for the column layout (there is no wrapper div — segments and bare blocks are direct `<article>` children) — h1/h2 headings and `.wide` blocks stand bare, the runs between them become `<div class="colseg">` (margin-breakout boxes — `.margin`, `::: aside` — stay inside the segment at their anchor point; the CSS positions them out of flow into the side zone) (plus `.cols` on segments with enough text in at least two paragraphs or one long enough to split across columns, `::: nocols` opting out; in column segments, paragraphs past `BREAKABLE_TEXT` visible characters are marked `.breakable` so they may split across columns), and `multicol` flags bodies long enough to columnize (visible-text thresholds, code excluded). `views.py` puts the class on the article; pagerite.css takes it from there (at most two columns, the left-margin breakout, all viewport adaptation).
|
`render()` returns a `Rendered(html, multicol)`: the article content segmented for the column layout (there is no wrapper div — segments and bare blocks are direct `<article>` children) — h1/h2 headings and `.wide` blocks stand bare, the runs between them become `<div class="colseg">` (margin-breakout boxes — `.margin`, `::: aside` — stay inside the segment at their anchor point; the CSS positions them out of flow into the side zone) (plus `.cols` on segments with enough text in at least two paragraphs or one long enough to split across columns, `::: nocols` opting out; in column segments, paragraphs past `BREAKABLE_TEXT` visible characters are marked `.breakable` so they may split across columns), and `multicol` flags bodies long enough to columnize (visible-text thresholds, code excluded). `views.py` puts the class on the article; pagerite.css takes it from there (at most two columns, the left-margin breakout, all viewport adaptation).
|
||||||
|
|
||||||
|
|||||||
@@ -33,14 +33,9 @@ Deliberately simple — **q-values are ignored**:
|
|||||||
- Selection rule (`select_language` in `pagerite/i18n.py`):
|
- Selection rule (`select_language` in `pagerite/i18n.py`):
|
||||||
1. If `?lang=<tag>` is present, use it (if a translation exists; otherwise
|
1. If `?lang=<tag>` is present, use it (if a translation exists; otherwise
|
||||||
fall through to header logic).
|
fall through to header logic).
|
||||||
2. If the article's original language appears anywhere in the header list,
|
2. Otherwise walk the header list in order and use the first language that
|
||||||
use the **original**. Rationale: an AI translation is strictly worse
|
can be served — the original, or one with an available translation.
|
||||||
than the original for anyone who has that language configured at all
|
3. Fall back to the original.
|
||||||
(e.g. `fi-FI, fi, en-US, en` gets English, not machine-translated
|
|
||||||
Finnish).
|
|
||||||
3. Otherwise walk the header list in order and use the first language for
|
|
||||||
which a translation exists.
|
|
||||||
4. Fall back to the original.
|
|
||||||
|
|
||||||
Region tags normalize to their base subtag (`fi-FI` → `fi`).
|
Region tags normalize to their base subtag (`fi-FI` → `fi`).
|
||||||
|
|
||||||
|
|||||||
@@ -23,6 +23,7 @@ import {
|
|||||||
formatVisitRows,
|
formatVisitRows,
|
||||||
} from './analytics/format.js'
|
} from './analytics/format.js'
|
||||||
import TrailLink from './TrailLink.vue'
|
import TrailLink from './TrailLink.vue'
|
||||||
|
import RefererBadge from './RefererBadge.vue'
|
||||||
import VisitorCell from './VisitorCell.vue'
|
import VisitorCell from './VisitorCell.vue'
|
||||||
import TransitionGraph from './TransitionGraph.vue'
|
import TransitionGraph from './TransitionGraph.vue'
|
||||||
import VisitorCharts from './VisitorCharts.vue'
|
import VisitorCharts from './VisitorCharts.vue'
|
||||||
@@ -133,7 +134,8 @@ onUnmounted(() => {
|
|||||||
const window = computed(() => rangeWindow(range.value))
|
const window = computed(() => rangeWindow(range.value))
|
||||||
|
|
||||||
// All non-chart stats follow the selected range; the charts keep their own
|
// All non-chart stats follow the selected range; the charts keep their own
|
||||||
// range-specific x windows (week overlays previous weeks aligned to Monday).
|
// range-specific x windows (week aligned to Monday, overlaid with the
|
||||||
|
// seasonal "typical week" curve).
|
||||||
const rangeData = computed(() => {
|
const rangeData = computed(() => {
|
||||||
if (!data.value) return null
|
if (!data.value) return null
|
||||||
const { t0, t1 } = window.value
|
const { t0, t1 } = window.value
|
||||||
@@ -160,9 +162,15 @@ watch(range, (r) => {
|
|||||||
|
|
||||||
const clients = computed(() => data.value?.clients || {})
|
const clients = computed(() => data.value?.clients || {})
|
||||||
const favicons = computed(() => data.value?.favicons || {})
|
const favicons = computed(() => data.value?.favicons || {})
|
||||||
const visitRows = computed(() => formatVisitRows(visits.value, clients.value, pageTree.value, now.value))
|
// Site language context from the payload: drives the discreet rendered-
|
||||||
|
// language markers in the visit/crawler rows (multilingual sites only).
|
||||||
|
const site = computed(() => ({
|
||||||
|
multilingual: !!data.value?.multilingual,
|
||||||
|
primaryLang: data.value?.primary_lang || '',
|
||||||
|
}))
|
||||||
|
const visitRows = computed(() => formatVisitRows(visits.value, clients.value, pageTree.value, now.value, site.value))
|
||||||
const crawlers = computed(() => rangeData.value?.crawlers || [])
|
const crawlers = computed(() => rangeData.value?.crawlers || [])
|
||||||
const crawlerRows = computed(() => formatCrawlerRows(crawlers.value, clients.value, pageTree.value, now.value))
|
const crawlerRows = computed(() => formatCrawlerRows(crawlers.value, clients.value, pageTree.value, now.value, site.value))
|
||||||
const abuseRows = computed(() => formatAbuseRows(rangeData.value?.abuse || [], clients.value, pageTree.value, now.value))
|
const abuseRows = computed(() => formatAbuseRows(rangeData.value?.abuse || [], clients.value, pageTree.value, now.value))
|
||||||
|
|
||||||
</script>
|
</script>
|
||||||
@@ -209,9 +217,9 @@ const abuseRows = computed(() => formatAbuseRows(rangeData.value?.abuse || [], c
|
|||||||
<tbody>
|
<tbody>
|
||||||
<tr v-for="(v, i) in visitRows" :key="i">
|
<tr v-for="(v, i) in visitRows" :key="i">
|
||||||
<td class="trail">
|
<td class="trail">
|
||||||
<TrailLink v-if="v.refererStep" :step="v.refererStep" :favicons="favicons" @close="$emit('close')" />
|
<RefererBadge v-if="v.refererBadge" :badge="v.refererBadge" :favicons="favicons" />
|
||||||
<span v-if="v.utm && v.utm !== '—'" class="utm-tag small muted" :title="v.utmTitle">{{ v.utm }}</span>
|
<span v-if="v.rowFlag" class="flag" v-html="v.rowFlag" :title="v.rowFlagTitle"></span>
|
||||||
<TrailLink v-for="(s, si) in v.trail" :key="si" :step="s" :favicons="favicons" @close="$emit('close')" />
|
<TrailLink v-for="(s, si) in v.trail" :key="si" :step="s" :favicons="favicons" :flags="s.langFlags" @close="$emit('close')" />
|
||||||
</td>
|
</td>
|
||||||
<VisitorCell
|
<VisitorCell
|
||||||
:ip="v.ip"
|
:ip="v.ip"
|
||||||
@@ -246,8 +254,9 @@ const abuseRows = computed(() => formatAbuseRows(rangeData.value?.abuse || [], c
|
|||||||
<tbody>
|
<tbody>
|
||||||
<tr v-for="(c, i) in crawlerRows" :key="i">
|
<tr v-for="(c, i) in crawlerRows" :key="i">
|
||||||
<td class="trail">
|
<td class="trail">
|
||||||
<TrailLink v-if="c.refererStep" :step="c.refererStep" :favicons="favicons" @close="$emit('close')" />
|
<RefererBadge v-if="c.refererBadge" :badge="c.refererBadge" :favicons="favicons" />
|
||||||
<TrailLink v-for="(s, si) in c.pages" :key="si" :step="s" :count="s.count" @close="$emit('close')" />
|
<TrailLink v-for="(s, si) in c.pages" :key="si" :step="s" :count="s.count" @close="$emit('close')" />
|
||||||
|
<span v-for="(f, fi) in c.readFlags" :key="fi" class="flag" v-html="f.flag" :title="f.name"></span>
|
||||||
</td>
|
</td>
|
||||||
<VisitorCell
|
<VisitorCell
|
||||||
:ip="c.ip"
|
:ip="c.ip"
|
||||||
@@ -472,16 +481,39 @@ const abuseRows = computed(() => formatAbuseRows(rangeData.value?.abuse || [], c
|
|||||||
color: var(--error, #c00);
|
color: var(--error, #c00);
|
||||||
}
|
}
|
||||||
|
|
||||||
.visit-table .utm-tag {
|
/* The referer badge outgrows the 8rem trail-link cap (it carries the UTM
|
||||||
display: inline-block;
|
summary too); keep the inline-flex layout from the component. The
|
||||||
|
generic trail-link rule above would otherwise clip the badge (overflow:
|
||||||
|
hidden, hiding the absolutely positioned favicon) and cap its inner
|
||||||
|
link — the link is display: contents, so its parts lay out as badge
|
||||||
|
flex items. */
|
||||||
|
.visit-table .trail .referer-badge {
|
||||||
|
display: inline-flex;
|
||||||
max-width: 100%;
|
max-width: 100%;
|
||||||
padding: 0.05rem 0.4rem;
|
overflow: visible;
|
||||||
border: 1px solid var(--line);
|
}
|
||||||
border-radius: 0.25rem;
|
|
||||||
white-space: nowrap;
|
.visit-table .trail .referer-badge a.badge-link {
|
||||||
|
display: contents;
|
||||||
|
}
|
||||||
|
|
||||||
|
/* Same flag chip as the visitor cells (VisitorCell.vue); the flags here
|
||||||
|
mark the language the page was read in. */
|
||||||
|
.visit-table .flag {
|
||||||
|
display: inline-flex;
|
||||||
|
width: 18px;
|
||||||
|
height: 12px;
|
||||||
|
border-radius: 2px;
|
||||||
overflow: hidden;
|
overflow: hidden;
|
||||||
text-overflow: ellipsis;
|
border: 1px solid var(--line);
|
||||||
vertical-align: bottom;
|
box-shadow: 0 0 0 1px rgba(0, 0, 0, 0.2) inset;
|
||||||
|
vertical-align: middle;
|
||||||
|
}
|
||||||
|
|
||||||
|
.visit-table .flag :deep(svg) {
|
||||||
|
width: 100%;
|
||||||
|
height: 100%;
|
||||||
|
display: block;
|
||||||
}
|
}
|
||||||
|
|
||||||
.visit-table .clickable-list {
|
.visit-table .clickable-list {
|
||||||
|
|||||||
@@ -736,17 +736,15 @@ function previewIntoArticle(html, multicol) {
|
|||||||
if (!article) return
|
if (!article) return
|
||||||
// The server render owns the article completely — the injected title h1,
|
// The server render owns the article completely — the injected title h1,
|
||||||
// the column layout (.multicol on the article, the .colseg/.cols
|
// the column layout (.multicol on the article, the .colseg/.cols
|
||||||
// segments) — so the whole article content swaps as one. Only the edit
|
// segments), the card stacks ({cards} tags expanded, or the children's
|
||||||
// pen and the category cards survive: detach them before innerHTML wipes
|
// cards appended when the page has no tag) — so the whole article
|
||||||
// them. pagerite.js re-places the pen into the first visible h1 on
|
// content swaps as one. Only the edit pen survives: detach it before
|
||||||
// pagerite:preview.
|
// innerHTML wipes it. pagerite.js re-places the pen into the first
|
||||||
|
// visible h1 on pagerite:preview.
|
||||||
article.classList.toggle('multicol', multicol)
|
article.classList.toggle('multicol', multicol)
|
||||||
const pen = article.querySelector('button.edit-link')
|
const pen = article.querySelector('button.edit-link')
|
||||||
if (pen) pen.remove()
|
if (pen) pen.remove()
|
||||||
const cards = article.querySelector(':scope > .cards')
|
|
||||||
if (cards) cards.remove()
|
|
||||||
article.innerHTML = html
|
article.innerHTML = html
|
||||||
if (cards) article.append(cards)
|
|
||||||
runScripts(article)
|
runScripts(article)
|
||||||
dispatchEvent(new CustomEvent('pagerite:preview'))
|
dispatchEvent(new CustomEvent('pagerite:preview'))
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -0,0 +1,113 @@
|
|||||||
|
<script setup>
|
||||||
|
// Referer + UTM as one badge in the analytics visit/crawler tables: the
|
||||||
|
// referer's favicon flush on the left, its host as the link text, then the
|
||||||
|
// UTM summary smaller/muted inside the same badge. Only the favicon and
|
||||||
|
// host are the link (external, new tab) — everything else, padding and
|
||||||
|
// UTM text included, copies the full utm tag list to the clipboard. The
|
||||||
|
// link is display: contents so its parts lay out as badge flex items.
|
||||||
|
// The badge carries a single one-fact-per-line tooltip (badge.title:
|
||||||
|
// origin, then each utm pair) — no titles on the inner elements.
|
||||||
|
// Referers are external, so there is no close event.
|
||||||
|
import { computed } from 'vue'
|
||||||
|
import { copyList } from './analytics/format.js'
|
||||||
|
|
||||||
|
const props = defineProps({
|
||||||
|
badge: { type: Object, required: true },
|
||||||
|
favicons: { type: Object, default: null },
|
||||||
|
})
|
||||||
|
|
||||||
|
const favicon = computed(() => (props.badge.origin ? props.favicons?.[props.badge.origin] : null))
|
||||||
|
</script>
|
||||||
|
|
||||||
|
<template>
|
||||||
|
<span class="referer-badge"
|
||||||
|
:class="{ 'with-icon': favicon, copyable: badge.utm }"
|
||||||
|
:title="badge.title"
|
||||||
|
@click="badge.utm && copyList(badge.utmCopy, $event)">
|
||||||
|
<a v-if="badge.href" class="badge-link" :href="badge.href"
|
||||||
|
target="_blank" rel="noopener" @click.stop>
|
||||||
|
<img v-if="favicon" class="badge-favicon" :src="favicon" alt="" />
|
||||||
|
<span v-if="badge.label">{{ badge.label }}</span>
|
||||||
|
</a>
|
||||||
|
<template v-else>
|
||||||
|
<img v-if="favicon" class="badge-favicon" :src="favicon" alt="" />
|
||||||
|
<span v-if="badge.label">{{ badge.label }}</span>
|
||||||
|
</template>
|
||||||
|
<small v-if="badge.utm" class="small">{{ badge.utm }}</small>
|
||||||
|
</span>
|
||||||
|
</template>
|
||||||
|
|
||||||
|
<style scoped>
|
||||||
|
/* Browser-chrome chip on a translucent neutral wash (--badge-* in
|
||||||
|
pagerite.css, deliberately unthemed): black-on-transparent and
|
||||||
|
white-on-transparent favicons both stay legible on it. Colors go on the
|
||||||
|
inner elements, so the theme's link color rules cannot cascade in. The
|
||||||
|
padding is matched by negative margins so the chip's content stays
|
||||||
|
exactly where the bare text would sit without the badge — except on the
|
||||||
|
right, which keeps a small positive margin so the next trail item does
|
||||||
|
not abut the chip. */
|
||||||
|
.referer-badge {
|
||||||
|
position: relative;
|
||||||
|
display: inline-flex;
|
||||||
|
align-items: center;
|
||||||
|
gap: 0.35em;
|
||||||
|
/* Fixed line-height: the bar height is then exactly 1.2em + padding =
|
||||||
|
1.6em, so the icon below can be sized to match precisely (an
|
||||||
|
absolutely positioned replaced element cannot derive its height from
|
||||||
|
top/bottom offsets — its aspect ratio wins and bottom is dropped). */
|
||||||
|
line-height: 1.2;
|
||||||
|
padding: 0.2em 0.5em;
|
||||||
|
margin: -0.2em 0.25em -0.2em -0.2em;
|
||||||
|
/* Fully rounded: the bar is exactly 1.6em tall, so a 0.8em radius makes
|
||||||
|
both ends semicircles — a pill, with a full circle around the favicon
|
||||||
|
on the left. */
|
||||||
|
border-radius: 0.8em;
|
||||||
|
background: var(--badge-bg);
|
||||||
|
color: var(--badge-text);
|
||||||
|
white-space: nowrap;
|
||||||
|
}
|
||||||
|
|
||||||
|
/* Room for the absolutely positioned icon (its 1.6em width plus the gap). */
|
||||||
|
.referer-badge.with-icon {
|
||||||
|
padding-left: 1.95em;
|
||||||
|
}
|
||||||
|
|
||||||
|
/* Exactly the bar's height (1.6em, see line-height above), flush to the
|
||||||
|
top/left/bottom borders. The badge does not clip it (no overflow:
|
||||||
|
hidden): the icon may stick out past the bar's rounded corners.
|
||||||
|
Absolute on purpose: an in-flow image is the flex
|
||||||
|
container's first item and would supply the badge's baseline (an image's
|
||||||
|
baseline is its bottom edge), pushing the badge text above the baseline
|
||||||
|
of the trail items that follow. Out of flow, the badge's baseline comes
|
||||||
|
from its text, so baselines match. */
|
||||||
|
.badge-favicon {
|
||||||
|
position: absolute;
|
||||||
|
top: 0;
|
||||||
|
left: 0;
|
||||||
|
width: 1.6em;
|
||||||
|
height: 1.6em;
|
||||||
|
object-fit: cover;
|
||||||
|
}
|
||||||
|
|
||||||
|
/* The link is display: contents: the favicon and label lay out as flex
|
||||||
|
items of the badge itself, and only their actual boxes are clickable. */
|
||||||
|
.badge-link {
|
||||||
|
display: contents;
|
||||||
|
}
|
||||||
|
|
||||||
|
/* Click-to-copy affordance on everything outside the link (the UTM text
|
||||||
|
and the surrounding padding). */
|
||||||
|
.referer-badge.copyable {
|
||||||
|
cursor: pointer;
|
||||||
|
}
|
||||||
|
|
||||||
|
.referer-badge span,
|
||||||
|
.referer-badge small {
|
||||||
|
min-width: 0;
|
||||||
|
overflow: hidden;
|
||||||
|
text-overflow: ellipsis;
|
||||||
|
}
|
||||||
|
|
||||||
|
.referer-badge span { color: var(--badge-text); }
|
||||||
|
.referer-badge small { color: var(--badge-muted); }
|
||||||
|
</style>
|
||||||
@@ -6,6 +6,7 @@ const props = defineProps({
|
|||||||
step: { type: Object, required: true },
|
step: { type: Object, required: true },
|
||||||
count: { type: Number, default: 0 },
|
count: { type: Number, default: 0 },
|
||||||
favicons: { type: Object, default: null },
|
favicons: { type: Object, default: null },
|
||||||
|
flags: { type: Array, default: () => [] },
|
||||||
})
|
})
|
||||||
|
|
||||||
defineEmits(['close'])
|
defineEmits(['close'])
|
||||||
@@ -38,6 +39,7 @@ const title = computed(() => {
|
|||||||
<small v-if="count > 1" class="muted">{{ formatCount(count) }}×</small>
|
<small v-if="count > 1" class="muted">{{ formatCount(count) }}×</small>
|
||||||
<img v-if="favicon" class="favicon" :src="favicon" alt="" />
|
<img v-if="favicon" class="favicon" :src="favicon" alt="" />
|
||||||
<span>{{ step.slug }}</span>
|
<span>{{ step.slug }}</span>
|
||||||
|
<span v-for="(f, fi) in flags" :key="fi" class="flag" v-html="f"></span>
|
||||||
</a>
|
</a>
|
||||||
</template>
|
</template>
|
||||||
|
|
||||||
@@ -48,4 +50,23 @@ const title = computed(() => {
|
|||||||
margin-right: 0.25em;
|
margin-right: 0.25em;
|
||||||
vertical-align: -0.1em;
|
vertical-align: -0.1em;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
/* Same flag chip as the visitor cells (VisitorCell.vue). */
|
||||||
|
.flag {
|
||||||
|
display: inline-flex;
|
||||||
|
width: 18px;
|
||||||
|
height: 12px;
|
||||||
|
margin-left: 0.25em;
|
||||||
|
border-radius: 2px;
|
||||||
|
overflow: hidden;
|
||||||
|
border: 1px solid var(--line);
|
||||||
|
box-shadow: 0 0 0 1px rgba(0, 0, 0, 0.2) inset;
|
||||||
|
vertical-align: middle;
|
||||||
|
}
|
||||||
|
|
||||||
|
.flag :deep(svg) {
|
||||||
|
width: 100%;
|
||||||
|
height: 100%;
|
||||||
|
display: block;
|
||||||
|
}
|
||||||
</style>
|
</style>
|
||||||
|
|||||||
@@ -257,11 +257,14 @@ const countLabel = (n) =>
|
|||||||
filter: drop-shadow(0 0 2.5px var(--accent));
|
filter: drop-shadow(0 0 2.5px var(--accent));
|
||||||
}
|
}
|
||||||
.tmap .txnode {
|
.tmap .txnode {
|
||||||
fill: var(--text);
|
/* External source/exit pills: plain white on every theme, with a hairline
|
||||||
stroke: none;
|
so the pill stays visible on a white page. */
|
||||||
|
fill: #fff;
|
||||||
|
stroke: var(--line, rgba(128, 128, 128, 0.4));
|
||||||
|
stroke-width: 1;
|
||||||
}
|
}
|
||||||
.tmap .txnode-source { fill: var(--text); }
|
.tmap .txnode-source { fill: #fff; }
|
||||||
.tmap .txnode-exit { fill: var(--text); }
|
.tmap .txnode-exit { fill: #fff; }
|
||||||
/* Branch lanes: one wide concentric arc per path prefix, running behind
|
/* Branch lanes: one wide concentric arc per path prefix, running behind
|
||||||
the node pills around the fan's circle center; parent levels sit one
|
the node pills around the fan's circle center; parent levels sit one
|
||||||
indent (radius step) outward. Each lane's label follows a short guide
|
indent (radius step) outward. Each lane's label follows a short guide
|
||||||
@@ -289,15 +292,18 @@ const countLabel = (n) =>
|
|||||||
stroke: none;
|
stroke: none;
|
||||||
}
|
}
|
||||||
/* Text sizes are viewBox units: they shrink along with the graph on
|
/* Text sizes are viewBox units: they shrink along with the graph on
|
||||||
narrow panels. Overlong labels are clipped at the pill border. */
|
narrow panels. Overlong labels are clipped at the pill border. The text
|
||||||
|
is always black, on accent (internal pills) and white (external pills)
|
||||||
|
alike — black stands out from any accent color, so the coloring stays
|
||||||
|
stable across themes and light/dark modes. */
|
||||||
.tmap .tnodeslug {
|
.tmap .tnodeslug {
|
||||||
fill: var(--bg, Canvas);
|
fill: #000;
|
||||||
font-size: 19px;
|
font-size: 19px;
|
||||||
text-anchor: start;
|
text-anchor: start;
|
||||||
}
|
}
|
||||||
.tmap a { cursor: pointer; }
|
.tmap a { cursor: pointer; }
|
||||||
.tmap .tnodecount {
|
.tmap .tnodecount {
|
||||||
fill: var(--bg, Canvas);
|
fill: #000;
|
||||||
opacity: 0.75;
|
opacity: 0.75;
|
||||||
font-size: 15px;
|
font-size: 15px;
|
||||||
text-anchor: middle;
|
text-anchor: middle;
|
||||||
|
|||||||
@@ -4,6 +4,7 @@
|
|||||||
*/
|
*/
|
||||||
import { computed, onMounted, onUnmounted, ref } from 'vue'
|
import { computed, onMounted, onUnmounted, ref } from 'vue'
|
||||||
import { makeSeries } from './analytics/time.js'
|
import { makeSeries } from './analytics/time.js'
|
||||||
|
import { typicalWeek, weekBinIndex } from './analytics/seasonal.js'
|
||||||
import {
|
import {
|
||||||
CHART_H,
|
CHART_H,
|
||||||
CHART_W,
|
CHART_W,
|
||||||
@@ -35,9 +36,6 @@ const allViews = computed(() => {
|
|||||||
return all
|
return all
|
||||||
})
|
})
|
||||||
|
|
||||||
const visitSeries = computed(() => makeSeries(props.data?.site_visits, props.range))
|
|
||||||
const viewSeries = computed(() => makeSeries(allViews.value, props.range))
|
|
||||||
|
|
||||||
function freqLabel(unit) {
|
function freqLabel(unit) {
|
||||||
return unit === '5min' ? '5 min' : unit === 'hour' ? 'hourly' : 'daily'
|
return unit === '5min' ? '5 min' : unit === 'hour' ? 'hourly' : 'daily'
|
||||||
}
|
}
|
||||||
@@ -47,12 +45,6 @@ function axisLabel(unit, ylabel) {
|
|||||||
return unit === '5min' ? `${ylabel} / 5 min` : `${freqLabel(unit)} ${ylabel}`
|
return unit === '5min' ? `${ylabel} / 5 min` : `${freqLabel(unit)} ${ylabel}`
|
||||||
}
|
}
|
||||||
|
|
||||||
/** Legend label for the overlaid past weeks: "Week M" or "Week M–N". */
|
|
||||||
function pastLabel(series) {
|
|
||||||
const oldest = series.at(-1).label.slice(5) // strip "Week "
|
|
||||||
return series.length > 2 ? `Week ${oldest}–${series[1].label.slice(5)}` : `Week ${oldest}`
|
|
||||||
}
|
|
||||||
|
|
||||||
const now = ref(Date.now())
|
const now = ref(Date.now())
|
||||||
let refreshInterval = null
|
let refreshInterval = null
|
||||||
onMounted(() => {
|
onMounted(() => {
|
||||||
@@ -62,8 +54,29 @@ onUnmounted(() => {
|
|||||||
if (refreshInterval) clearInterval(refreshInterval)
|
if (refreshInterval) clearInterval(refreshInterval)
|
||||||
})
|
})
|
||||||
|
|
||||||
const visitChart = computed(() => buildChart(visitSeries.value, now.value))
|
/**
|
||||||
const viewChart = computed(() => buildChart(viewSeries.value, now.value))
|
* Series for the current range plus, on the day and week views, the
|
||||||
|
* seasonal "typical week" history curve (all history up to now, already
|
||||||
|
* smoothed). Week view: the full Monday-first week. Day view: the rolling
|
||||||
|
* window's bins looked up from the same estimate, labeled by the weekday.
|
||||||
|
*/
|
||||||
|
function withTypical(buckets) {
|
||||||
|
const input = makeSeries(buckets, props.range)
|
||||||
|
if (props.range !== 'day' && props.range !== 'week') return input
|
||||||
|
const estimate = typicalWeek(buckets, now.value)
|
||||||
|
if (!estimate) return input
|
||||||
|
if (props.range === 'week') {
|
||||||
|
return { ...input, typical: { values: [...estimate], label: 'Typical week' } }
|
||||||
|
}
|
||||||
|
const values = input.series[0].points.map((p) => estimate[weekBinIndex(p.t)])
|
||||||
|
const weekday = new Date(now.value).toLocaleDateString(undefined, {
|
||||||
|
weekday: 'long', timeZone: 'UTC',
|
||||||
|
})
|
||||||
|
return { ...input, typical: { values, label: `Typical ${weekday}` } }
|
||||||
|
}
|
||||||
|
|
||||||
|
const visitChart = computed(() => buildChart(withTypical(props.data?.site_visits), now.value))
|
||||||
|
const viewChart = computed(() => buildChart(withTypical(allViews.value), now.value))
|
||||||
</script>
|
</script>
|
||||||
|
|
||||||
<template>
|
<template>
|
||||||
@@ -75,8 +88,7 @@ const viewChart = computed(() => buildChart(viewSeries.value, now.value))
|
|||||||
<svg class="chart" :viewBox="`${-MARGIN_L} 0 ${VIEW_W} ${VIEW_H}`"
|
<svg class="chart" :viewBox="`${-MARGIN_L} 0 ${VIEW_W} ${VIEW_H}`"
|
||||||
:style="{ maxWidth: `${VIEW_W}px`, marginLeft: CHART_MARGIN }"
|
:style="{ maxWidth: `${VIEW_W}px`, marginLeft: CHART_MARGIN }"
|
||||||
role="img" :aria-label="axisLabel(c.chart.unit, c.ylabel)">
|
role="img" :aria-label="axisLabel(c.chart.unit, c.ylabel)">
|
||||||
<!-- Clip the plot curves to the chart area: past-week overlays can
|
<!-- Clip the plot curves to the chart area; the svg itself is
|
||||||
run far above the autoscaled y range, and the svg itself is
|
|
||||||
overflow: visible for the axis labels. -->
|
overflow: visible for the axis labels. -->
|
||||||
<clipPath :id="`plot-${c.ylabel}`">
|
<clipPath :id="`plot-${c.ylabel}`">
|
||||||
<rect x="0" y="0" :width="CHART_W" :height="CHART_H" />
|
<rect x="0" y="0" :width="CHART_W" :height="CHART_H" />
|
||||||
@@ -88,17 +100,17 @@ const viewChart = computed(() => buildChart(viewSeries.value, now.value))
|
|||||||
class="minor vertical" />
|
class="minor vertical" />
|
||||||
</template>
|
</template>
|
||||||
<g :clip-path="`url(#plot-${c.ylabel})`">
|
<g :clip-path="`url(#plot-${c.ylabel})`">
|
||||||
|
<!-- The muted "typical" history curve under the current data. -->
|
||||||
|
<path v-if="c.chart.typical" :d="c.chart.typical.line" class="line past" />
|
||||||
<template v-if="c.chart.bars">
|
<template v-if="c.chart.bars">
|
||||||
<rect v-for="(b, i) in c.chart.bars" :key="'b' + i"
|
<rect v-for="(b, i) in c.chart.bars" :key="'b' + i"
|
||||||
:x="b.x" :y="b.y" :width="b.width" :height="b.height" class="bar" />
|
:x="b.x" :y="b.y" :width="b.width" :height="b.height" class="bar" />
|
||||||
<path :d="c.chart.skyline" class="line" />
|
<path :d="c.chart.skyline" class="line" />
|
||||||
</template>
|
</template>
|
||||||
<template v-else>
|
<template v-else>
|
||||||
<!-- Oldest overlay weeks first so the current week paints on top. -->
|
<template v-for="(s, i) in c.chart.series" :key="i">
|
||||||
<template v-for="(s, i) in [...c.chart.series].reverse()" :key="i">
|
|
||||||
<path v-if="s.area" :d="s.area" class="area" />
|
<path v-if="s.area" :d="s.area" class="area" />
|
||||||
<path :d="s.line" class="line" :class="{ past: s.past }"
|
<path :d="s.line" class="line" />
|
||||||
:style="{ opacity: s.opacity }" />
|
|
||||||
</template>
|
</template>
|
||||||
</template>
|
</template>
|
||||||
</g>
|
</g>
|
||||||
@@ -111,16 +123,17 @@ const viewChart = computed(() => buildChart(viewSeries.value, now.value))
|
|||||||
class="yaxis-label">{{ axisLabel(c.chart.unit, c.ylabel) }}</text>
|
class="yaxis-label">{{ axisLabel(c.chart.unit, c.ylabel) }}</text>
|
||||||
<text v-for="t in c.chart.xticks" :key="'x' + t.x" :x="t.x" :y="CHART_H + MARGIN_B - 8"
|
<text v-for="t in c.chart.xticks" :key="'x' + t.x" :x="t.x" :y="CHART_H + MARGIN_B - 8"
|
||||||
text-anchor="middle" class="xlab">{{ t.label }}</text>
|
text-anchor="middle" class="xlab">{{ t.label }}</text>
|
||||||
<!-- Week overlay legend, top right inside the plot: current week in
|
<!-- Legend, top right inside the plot: current data in accent
|
||||||
accent, one muted specimen for the whole past range. -->
|
(week label, or "Last 24 hours" on the day view) and the
|
||||||
<g v-if="c.legend && c.chart.series.length > 1">
|
typical history curve in muted. -->
|
||||||
<line :x1="CHART_W - 98" :x2="CHART_W - 78" y1="10" y2="10" class="line" />
|
<g v-if="c.legend && c.chart.typical">
|
||||||
<text :x="CHART_W - 72" y="10" dominant-baseline="middle"
|
<line :x1="CHART_W - 118" :x2="CHART_W - 98" y1="10" y2="10" class="line" />
|
||||||
class="leglab">{{ c.chart.series[0].label }}</text>
|
<text :x="CHART_W - 92" y="10" dominant-baseline="middle"
|
||||||
<line :x1="CHART_W - 98" :x2="CHART_W - 78" y1="25" y2="25"
|
class="leglab">{{ c.chart.bars ? 'Last 24 hours' : c.chart.series[0].label }}</text>
|
||||||
|
<line :x1="CHART_W - 118" :x2="CHART_W - 98" y1="25" y2="25"
|
||||||
class="line past" style="opacity: 0.6" />
|
class="line past" style="opacity: 0.6" />
|
||||||
<text :x="CHART_W - 72" y="25" dominant-baseline="middle"
|
<text :x="CHART_W - 92" y="25" dominant-baseline="middle"
|
||||||
class="leglab">{{ pastLabel(c.chart.series) }}</text>
|
class="leglab">{{ c.chart.typical.label }}</text>
|
||||||
</g>
|
</g>
|
||||||
</svg>
|
</svg>
|
||||||
</template>
|
</template>
|
||||||
@@ -183,12 +196,12 @@ const viewChart = computed(() => buildChart(viewSeries.value, now.value))
|
|||||||
|
|
||||||
.chart .area {
|
.chart .area {
|
||||||
fill: var(--accent);
|
fill: var(--accent);
|
||||||
opacity: 0.15;
|
opacity: 0.6;
|
||||||
}
|
}
|
||||||
|
|
||||||
.chart .bar {
|
.chart .bar {
|
||||||
fill: var(--accent);
|
fill: var(--accent);
|
||||||
opacity: 0.15;
|
opacity: 0.6;
|
||||||
}
|
}
|
||||||
|
|
||||||
.chart .line {
|
.chart .line {
|
||||||
|
|||||||
@@ -181,16 +181,21 @@ export function spline(pts) {
|
|||||||
export function buildChart(input, now = Date.now()) {
|
export function buildChart(input, now = Date.now()) {
|
||||||
if (!input || !input.series.length) return null
|
if (!input || !input.series.length) return null
|
||||||
if (input.unit === '5min') return buildDayChart(input, now)
|
if (input.unit === '5min') return buildDayChart(input, now)
|
||||||
const { series, t0, t1, rate, binMinutes, unitMinutes, unit } = input
|
const { series, t0, t1, rate, binMinutes, unitMinutes, unit, typical } = input
|
||||||
// Values are per-unit rates (hour on the week view, day on month+); the
|
// Values are per-unit rates (hour on the week view, day on month+); the
|
||||||
// y max is derived from the *smoothed* curves so random single-bucket
|
// y max is derived from the *smoothed* curves so random single-bucket
|
||||||
// spikes don't blow up the scale. Smoothing works on raw counts (its edge
|
// spikes don't blow up the scale. Smoothing works on raw counts (its edge
|
||||||
// detector thresholds are count-based), the result is scaled back to rates.
|
// detector thresholds are count-based), the result is scaled back to rates.
|
||||||
const smoothed = series.map((s) =>
|
const smoothed = series.map((s) =>
|
||||||
smooth(s.points.map((p) => p.count), binMinutes, unitMinutes).map((v) => v * rate))
|
smooth(s.points.map((p) => p.count), binMinutes, unitMinutes).map((v) => v * rate))
|
||||||
// Scale from the current/primary series only; older overlay weeks are drawn
|
// The "typical week" seasonal estimate is already smooth: one value per
|
||||||
// with the same scale and allowed to overflow if they are busier.
|
// bin spanning the full week (future included), drawn in the muted color.
|
||||||
const highest = Math.max(0, ...smoothed[0])
|
const typicalRates = typical
|
||||||
|
? [...typical.values].map((v) => v * rate)
|
||||||
|
: null
|
||||||
|
// Scale from the current series plus the typical curve; both are smooth,
|
||||||
|
// and neither should be clipped in normal traffic.
|
||||||
|
const highest = Math.max(0, ...smoothed[0], ...(typicalRates || []))
|
||||||
const { max, step, minor } = yScale(highest)
|
const { max, step, minor } = yScale(highest)
|
||||||
const x = (t) => ((t - t0) / (t1 - t0)) * CHART_W
|
const x = (t) => ((t - t0) / (t1 - t0)) * CHART_W
|
||||||
const y = (v) => PAD_TOP + (1 - Math.max(0, v) / max) * (CHART_H - PAD_TOP)
|
const y = (v) => PAD_TOP + (1 - Math.max(0, v) / max) * (CHART_H - PAD_TOP)
|
||||||
@@ -205,6 +210,12 @@ export function buildChart(input, now = Date.now()) {
|
|||||||
area: s.area ? `${line}L${last.x},${CHART_H}L${first.x},${CHART_H}Z` : null,
|
area: s.area ? `${line}L${last.x},${CHART_H}L${first.x},${CHART_H}Z` : null,
|
||||||
}
|
}
|
||||||
})
|
})
|
||||||
|
let typicalLine = null
|
||||||
|
if (typicalRates) {
|
||||||
|
const binMs = (t1 - t0) / typicalRates.length
|
||||||
|
const pts = typicalRates.map((v, i) => ({ x: x(t0 + i * binMs), y: y(v) }))
|
||||||
|
typicalLine = { line: spline(pts), label: typical.label }
|
||||||
|
}
|
||||||
// Major (labeled) and minor (hairline) y grid ticks.
|
// Major (labeled) and minor (hairline) y grid ticks.
|
||||||
const majors = []
|
const majors = []
|
||||||
const minors = []
|
const minors = []
|
||||||
@@ -256,16 +267,19 @@ export function buildChart(input, now = Date.now()) {
|
|||||||
x: x(t), label: fmtTick(t, t1 - t0), line: true,
|
x: x(t), label: fmtTick(t, t1 - t0), line: true,
|
||||||
}))
|
}))
|
||||||
}
|
}
|
||||||
return { max, majors, minors, series: drawn, xticks, unit }
|
return { max, majors, minors, series: drawn, typical: typicalLine, xticks, unit }
|
||||||
}
|
}
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* Day view: 5-minute bars for the last 24 hours. Bars are drawn at raw
|
* Day view: 5-minute bars for the last 24 hours. Bars are drawn at raw
|
||||||
* counts; the skyline uses a projected full-bucket value for the still-open
|
* counts; the skyline uses a projected full-bucket value for the still-open
|
||||||
* final bucket. The y scale is derived from the projected skyline maximum.
|
* final bucket. The y scale is derived from the projected skyline maximum.
|
||||||
|
* The optional "typical day" curve (per-bin counts aligned to the window's
|
||||||
|
* bins, cut from the typical-week estimate) overlays the bars as a smooth
|
||||||
|
* muted line and also feeds the y scale.
|
||||||
*/
|
*/
|
||||||
export function buildDayChart(input, now = Date.now()) {
|
export function buildDayChart(input, now = Date.now()) {
|
||||||
const { series, t0, t1 } = input
|
const { series, t0, t1, typical } = input
|
||||||
const points = series[0]?.points || []
|
const points = series[0]?.points || []
|
||||||
const n = points.length
|
const n = points.length
|
||||||
if (!n) return null
|
if (!n) return null
|
||||||
@@ -285,7 +299,7 @@ export function buildDayChart(input, now = Date.now()) {
|
|||||||
const share = elapsed / bucketMs
|
const share = elapsed / bucketMs
|
||||||
return p.count + prevRaw * (1 - share)
|
return p.count + prevRaw * (1 - share)
|
||||||
})
|
})
|
||||||
const highest = Math.max(0, ...projected)
|
const highest = Math.max(0, ...projected, ...(typical ? typical.values : []))
|
||||||
const { max, step, minor } = yScale(highest)
|
const { max, step, minor } = yScale(highest)
|
||||||
const y = (v) => PAD_TOP + (1 - Math.max(0, v) / max) * (CHART_H - PAD_TOP)
|
const y = (v) => PAD_TOP + (1 - Math.max(0, v) / max) * (CHART_H - PAD_TOP)
|
||||||
|
|
||||||
@@ -313,6 +327,15 @@ export function buildDayChart(input, now = Date.now()) {
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
let typicalLine = null
|
||||||
|
if (typical) {
|
||||||
|
const pts = points.map((p, i) => ({
|
||||||
|
x: (i + 0.5) * bucketWidth,
|
||||||
|
y: y(typical.values[i] || 0),
|
||||||
|
}))
|
||||||
|
typicalLine = { line: spline(pts), label: typical.label }
|
||||||
|
}
|
||||||
|
|
||||||
const majors = []
|
const majors = []
|
||||||
const minors = []
|
const minors = []
|
||||||
const nMajor = Math.round(max / step)
|
const nMajor = Math.round(max / step)
|
||||||
@@ -338,7 +361,7 @@ export function buildDayChart(input, now = Date.now()) {
|
|||||||
line: false,
|
line: false,
|
||||||
})
|
})
|
||||||
}
|
}
|
||||||
return { bars, skyline: skyline.trim(), max, majors, minors, xticks, unit: '5min', series: [] }
|
return { bars, skyline: skyline.trim(), typical: typicalLine, max, majors, minors, xticks, unit: '5min', series: [] }
|
||||||
}
|
}
|
||||||
|
|
||||||
/** X ticks for year/all: Monday boundaries up to a quarter, UTC month
|
/** X ticks for year/all: Monday boundaries up to a quarter, UTC month
|
||||||
|
|||||||
@@ -2,6 +2,7 @@
|
|||||||
* Formatters and aggregators for summary sections: totals and the recent
|
* Formatters and aggregators for summary sections: totals and the recent
|
||||||
* visit trail.
|
* visit trail.
|
||||||
*/
|
*/
|
||||||
|
import { flagFor, langName } from '../langs.js'
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* IPv4 unchanged, IPv6 returns the /64 network prefix in compact form.
|
* IPv4 unchanged, IPv6 returns the /64 network prefix in compact form.
|
||||||
@@ -176,6 +177,55 @@ function stepOf(path, titles) {
|
|||||||
return null
|
return null
|
||||||
}
|
}
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Badge data combining a visit's/crawler's external referer origin with the
|
||||||
|
* visit's UTM tags: the origin as the badge link/label (the favicon is
|
||||||
|
* looked up by origin in the component), a compact UTM summary (the few
|
||||||
|
* most informative values) as ``utm`` with the full ``utm_*=value`` list
|
||||||
|
* as ``utmCopy`` for click-to-copy, and a one-fact-per-line tooltip — the
|
||||||
|
* full origin URL on the first line, then every ``utm_*=value`` pair.
|
||||||
|
* Null when there is no external referer and no UTM tag (a plain direct
|
||||||
|
* visit).
|
||||||
|
*/
|
||||||
|
function refererBadgeOf(referer, titles, utmTags = {}) {
|
||||||
|
const step = stepOf(referer, titles)
|
||||||
|
const external = step?.external ? step : null
|
||||||
|
// Compact UTM summary, in display order source, campaign, content, term:
|
||||||
|
// source only when no referer is known (it just repeats where the visitor
|
||||||
|
// came from), content only as a stand-in when there is no term. The
|
||||||
|
// remaining tags (medium and any nonstandard utm_*) fill in only when
|
||||||
|
// fewer than three of these more useful items exist — and never when a
|
||||||
|
// term is present (the term alone says enough). The tooltip keeps
|
||||||
|
// every tag, one pair per line.
|
||||||
|
const useful = []
|
||||||
|
if (utmTags.utm_source && !referer) useful.push(utmTags.utm_source)
|
||||||
|
if (utmTags.utm_campaign) useful.push(utmTags.utm_campaign)
|
||||||
|
if (utmTags.utm_content && !utmTags.utm_term) useful.push(utmTags.utm_content)
|
||||||
|
if (utmTags.utm_term) useful.push(utmTags.utm_term)
|
||||||
|
const rest = useful.length < 3 && !utmTags.utm_term
|
||||||
|
? Object.keys(utmTags)
|
||||||
|
.filter((k) => !['utm_source', 'utm_campaign', 'utm_content', 'utm_term'].includes(k))
|
||||||
|
.map((k) => utmTags[k])
|
||||||
|
.filter(Boolean)
|
||||||
|
: []
|
||||||
|
const utm = [...useful, ...rest].join(' · ')
|
||||||
|
if (!external && !utm) return null
|
||||||
|
const utmCopy = Object.entries(utmTags)
|
||||||
|
.map(([k, value]) => `${k}=${value}`)
|
||||||
|
.join('\n')
|
||||||
|
return {
|
||||||
|
href: external?.origin || '',
|
||||||
|
label: external?.slug || '',
|
||||||
|
origin: external?.origin || '',
|
||||||
|
utm,
|
||||||
|
utmCopy,
|
||||||
|
title: [
|
||||||
|
...(external ? [external.origin] : []),
|
||||||
|
...Object.entries(utmTags).map(([k, value]) => `${k}=${value}`),
|
||||||
|
].join('\n'),
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* Human-readable relative timestamp. Adapted from cista-storage: uses
|
* Human-readable relative timestamp. Adapted from cista-storage: uses
|
||||||
* ``Intl.RelativeTimeFormat`` for short intervals and a compact date for
|
* ``Intl.RelativeTimeFormat`` for short intervals and a compact date for
|
||||||
@@ -368,12 +418,13 @@ export function mainDomain(host, limit = 24) {
|
|||||||
/**
|
/**
|
||||||
* Group raw crawler hits by client hash and format each group as a row showing
|
* Group raw crawler hits by client hash and format each group as a row showing
|
||||||
* every internal page that crawler visited. Rows are sorted by most recent hit
|
* every internal page that crawler visited. Rows are sorted by most recent hit
|
||||||
* first, with total hits as a tie-breaker. The group's ``refererStep`` is the
|
* first, with total hits as a tie-breaker. The group's ``refererBadge`` is
|
||||||
* latest external referer seen for the crawler — spiders often advertise
|
* the latest external referer seen for the crawler — spiders often advertise
|
||||||
* their own site there — rendered with its favicon like visit referers.
|
* their own site there — rendered as a badge with its favicon like visit
|
||||||
|
* referers.
|
||||||
* ``clients`` maps client hashes to client records.
|
* ``clients`` maps client hashes to client records.
|
||||||
*/
|
*/
|
||||||
export function formatCrawlerRows(crawlers, clients, pageTree, now = Date.now()) {
|
export function formatCrawlerRows(crawlers, clients, pageTree, now = Date.now(), site = { multilingual: false, primaryLang: '' }) {
|
||||||
const titles = buildTitleMap(pageTree)
|
const titles = buildTitleMap(pageTree)
|
||||||
const groups = new Map()
|
const groups = new Map()
|
||||||
for (const c of crawlers || []) {
|
for (const c of crawlers || []) {
|
||||||
@@ -384,10 +435,12 @@ export function formatCrawlerRows(crawlers, clients, pageTree, now = Date.now())
|
|||||||
lastStart: 0,
|
lastStart: 0,
|
||||||
referer: '',
|
referer: '',
|
||||||
pages: new Map(),
|
pages: new Map(),
|
||||||
|
langs: new Set(),
|
||||||
}
|
}
|
||||||
const start = new Date(c.start).getTime()
|
const start = new Date(c.start).getTime()
|
||||||
if (start > g.lastStart) g.lastStart = start
|
if (start > g.lastStart) g.lastStart = start
|
||||||
if (c.referer) g.referer = c.referer
|
if (c.referer) g.referer = c.referer
|
||||||
|
if (c.lang) g.langs.add(c.lang)
|
||||||
if (c.entry?.startsWith('/')) {
|
if (c.entry?.startsWith('/')) {
|
||||||
const existing = g.pages.get(c.entry) || { count: 0, status: c.status || 200 }
|
const existing = g.pages.get(c.entry) || { count: 0, status: c.status || 200 }
|
||||||
existing.count += 1
|
existing.count += 1
|
||||||
@@ -408,14 +461,22 @@ export function formatCrawlerRows(crawlers, clients, pageTree, now = Date.now())
|
|||||||
const client = g.client || {}
|
const client = g.client || {}
|
||||||
const host = client.host || ''
|
const host = client.host || ''
|
||||||
const isHost = !!host
|
const isHost = !!host
|
||||||
|
// Rendered languages read, shown only when they say something the
|
||||||
|
// primary language alone would not (multilingual sites only).
|
||||||
|
const langs = [...g.langs].sort()
|
||||||
|
const showLangs =
|
||||||
|
site.multilingual && (langs.length > 1 || (langs[0] && langs[0] !== site.primaryLang))
|
||||||
return {
|
return {
|
||||||
lastSeen: formatWhen(g.lastStart, now),
|
lastSeen: formatWhen(g.lastStart, now),
|
||||||
lastSeenIso: formatWhenIso(g.lastStart),
|
lastSeenIso: formatWhenIso(g.lastStart),
|
||||||
lastSeenLocal: formatWhenLocal(g.lastStart),
|
lastSeenLocal: formatWhenLocal(g.lastStart),
|
||||||
refererStep: stepOf(g.referer, titles),
|
refererBadge: refererBadgeOf(g.referer, titles),
|
||||||
pages: [...g.pages.entries()]
|
pages: [...g.pages.entries()]
|
||||||
.sort((a, b) => b[1].count - a[1].count)
|
.sort((a, b) => b[1].count - a[1].count)
|
||||||
.map(([path, info]) => ({ ...stepOf(path, titles), count: info.count, status: info.status })),
|
.map(([path, info]) => ({ ...stepOf(path, titles), count: info.count, status: info.status })),
|
||||||
|
readFlags: showLangs
|
||||||
|
? langs.map((l) => ({ flag: flagFor(l), name: langName(l) })).filter((f) => f.flag)
|
||||||
|
: [],
|
||||||
ip: client.ip || '',
|
ip: client.ip || '',
|
||||||
ipDisplay: isHost ? mainDomain(host) : hostIP(client.ip) || client.ip || '—',
|
ipDisplay: isHost ? mainDomain(host) : hostIP(client.ip) || client.ip || '—',
|
||||||
isHost,
|
isHost,
|
||||||
@@ -548,42 +609,57 @@ export function formatAbuseRows(abuse, clients, pageTree, now = Date.now()) {
|
|||||||
|
|
||||||
/**
|
/**
|
||||||
* Format raw visit records as rows for a technical table. Returns objects
|
* Format raw visit records as rows for a technical table. Returns objects
|
||||||
* with display strings; missing values become "—". ``trail`` starts with the
|
* with display strings; missing values become "—". The external referer
|
||||||
* external referer (when present), then the entry page and any further internal
|
* (when present) and the UTM tags ride along as ``refererBadge``; ``trail``
|
||||||
* pages or external exit origins. Only the 20 most recent visits are shown.
|
* holds the entry page and any further internal pages or external exit
|
||||||
* ``clients`` maps client hashes to client records.
|
* origins; consecutive views of the same page (e.g. a
|
||||||
|
* language switch re-view) merge into one step that keeps the
|
||||||
|
* consecutive-distinct rendered languages, summed read time, and the latest
|
||||||
|
* status. On multilingual sites the rendered languages surface as flag
|
||||||
|
* icons: a visit read entirely in one non-primary language gets ``rowFlag``,
|
||||||
|
* and a visit spanning languages gets per-step ``langFlags`` markers where
|
||||||
|
* the language begins or changes. Only the 20 most recent visits are shown.
|
||||||
|
* ``clients`` maps client hashes to client records; ``site`` carries the
|
||||||
|
* payload's multilingual/primary-language context.
|
||||||
*/
|
*/
|
||||||
export function formatVisitRows(visits, clients, pageTree, now = Date.now()) {
|
export function formatVisitRows(visits, clients, pageTree, now = Date.now(), site = { multilingual: false, primaryLang: '' }) {
|
||||||
const titles = buildTitleMap(pageTree)
|
const titles = buildTitleMap(pageTree)
|
||||||
return [...(visits || [])].reverse().slice(0, 20).map((v) => {
|
return [...(visits || [])].reverse().slice(0, 20).map((v) => {
|
||||||
const client = (clients || {})[v.client] || {}
|
const client = (clients || {})[v.client] || {}
|
||||||
const trail = Object.values(v.trail || {})
|
const steps = Object.values(v.trail || {})
|
||||||
.map((item) => {
|
.map((item) => {
|
||||||
const step = stepOf(item.to, titles)
|
const step = stepOf(item.to, titles)
|
||||||
if (step) {
|
if (step) {
|
||||||
if (item.read) step.readSeconds = item.read
|
if (item.read) step.readSeconds = item.read
|
||||||
if (item.status) step.status = item.status
|
if (item.status) step.status = item.status
|
||||||
|
if (item.lang) step.lang = item.lang
|
||||||
}
|
}
|
||||||
return step
|
return step
|
||||||
})
|
})
|
||||||
.filter(Boolean)
|
.filter(Boolean)
|
||||||
const utmKeys = ['utm_source', 'utm_medium', 'utm_campaign', 'utm_term', 'utm_content']
|
const trail = []
|
||||||
const utmValues = utmKeys.map((k) => (v.utm || {})[k]).filter(Boolean)
|
for (const step of steps) {
|
||||||
const utm = utmValues.length ? utmValues.join(' · ') : ''
|
const prev = trail[trail.length - 1]
|
||||||
const utmTitle = Object.entries(v.utm || {})
|
if (prev && prev.path === step.path) {
|
||||||
.map(([k, value]) => `${k}=${value}`)
|
if (step.lang && step.lang !== prev.langs[prev.langs.length - 1]) prev.langs.push(step.lang)
|
||||||
.join(', ')
|
if (step.readSeconds) prev.readSeconds = (prev.readSeconds || 0) + step.readSeconds
|
||||||
|
if (step.status) prev.status = step.status
|
||||||
|
} else {
|
||||||
|
step.langs = step.lang ? [step.lang] : []
|
||||||
|
trail.push(step)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
const distinctLangs = new Set(trail.flatMap((s) => s.langs))
|
||||||
const dash = (s) => (s || '—')
|
const dash = (s) => (s || '—')
|
||||||
const host = client.host || ''
|
const host = client.host || ''
|
||||||
const isHost = !!host
|
const isHost = !!host
|
||||||
return {
|
const row = {
|
||||||
lastSeen: formatWhen(v.start, now),
|
lastSeen: formatWhen(v.start, now),
|
||||||
lastSeenIso: formatWhenIso(v.start),
|
lastSeenIso: formatWhenIso(v.start),
|
||||||
lastSeenLocal: formatWhenLocal(v.start),
|
lastSeenLocal: formatWhenLocal(v.start),
|
||||||
langDisplay: formatLang(client.lang),
|
langDisplay: formatLang(client.lang),
|
||||||
trail,
|
trail,
|
||||||
refererStep: stepOf(v.referer, titles),
|
refererBadge: refererBadgeOf(v.referer, titles, v.utm),
|
||||||
referer: dash(v.referer),
|
|
||||||
ip: client.ip || '',
|
ip: client.ip || '',
|
||||||
ipDisplay: isHost ? mainDomain(host) : hostIP(client.ip) || client.ip || '—',
|
ipDisplay: isHost ? mainDomain(host) : hostIP(client.ip) || client.ip || '—',
|
||||||
isHost,
|
isHost,
|
||||||
@@ -593,8 +669,28 @@ export function formatVisitRows(visits, clients, pageTree, now = Date.now()) {
|
|||||||
ua: client.uarite?.pretty || client.ua || '—',
|
ua: client.uarite?.pretty || client.ua || '—',
|
||||||
uaRaw: client.ua || '',
|
uaRaw: client.ua || '',
|
||||||
uaUrl: client.uarite?.url || '',
|
uaUrl: client.uarite?.url || '',
|
||||||
utm: utm || '—',
|
|
||||||
utmTitle,
|
|
||||||
}
|
}
|
||||||
|
if (site.multilingual && distinctLangs.size) {
|
||||||
|
if (distinctLangs.size === 1) {
|
||||||
|
const [tag] = distinctLangs
|
||||||
|
const flag = flagFor(tag)
|
||||||
|
if (flag && tag !== site.primaryLang) {
|
||||||
|
row.rowFlag = flag
|
||||||
|
row.rowFlagTitle = langName(tag)
|
||||||
|
}
|
||||||
|
} else {
|
||||||
|
// Flag the steps where the rendered language begins or changes;
|
||||||
|
// lang-less steps keep the comparison chain going, they never flag.
|
||||||
|
let lastLang = null
|
||||||
|
for (const step of trail) {
|
||||||
|
if (!step.langs.length) continue
|
||||||
|
if (!lastLang || step.langs[step.langs.length - 1] !== lastLang) {
|
||||||
|
step.langFlags = step.langs.map(flagFor).filter(Boolean)
|
||||||
|
}
|
||||||
|
lastLang = step.langs[step.langs.length - 1]
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
return row
|
||||||
})
|
})
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -0,0 +1,109 @@
|
|||||||
|
/**
|
||||||
|
* Seasonal "typical week" estimate from the full visit history.
|
||||||
|
*
|
||||||
|
* Port of the seasonal.py demo algorithm: the whole smoothed 5-minute
|
||||||
|
* history is collapsed onto a weekly grid with exponential decay over age —
|
||||||
|
* a fast kernel (half-life 7 days) for the average time-of-day pattern and
|
||||||
|
* a slow one (half-life 42 days) for per-weekday deviations from it. The
|
||||||
|
* deviation is shrunk by the effective number of weeks behind each bin
|
||||||
|
* (n_eff / (n_eff + 3)), so with little history the estimate falls back to
|
||||||
|
* the common daily pattern and weekday character emerges as data accrues.
|
||||||
|
* Bins before the first recorded bucket are treated as missing.
|
||||||
|
*/
|
||||||
|
|
||||||
|
import { DAY, MIN5, mondayUTC, rawTimes } from './time.js'
|
||||||
|
import { smooth } from './chart.js'
|
||||||
|
|
||||||
|
export const BINS_PER_DAY = 288
|
||||||
|
export const BINS_PER_WEEK = 7 * BINS_PER_DAY
|
||||||
|
|
||||||
|
// History cap: at 180 days the slow kernel's weight is 2^(-180/42) ≈ 5%
|
||||||
|
// (and the fast kernel's utterly negligible), so older data cannot move
|
||||||
|
// this noisy estimate — skipping it keeps the smoothing pass O(1).
|
||||||
|
const MAX_HISTORY_DAYS = 180
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Estimate the typical week from a dense 5-minute count series (oldest
|
||||||
|
* first; non-finite values count as missing). endWeekBin is the week bin
|
||||||
|
* (Monday-first) just past the last sample. Returns BINS_PER_WEEK counts
|
||||||
|
* per 5-minute bin, starting Monday 00:00.
|
||||||
|
*/
|
||||||
|
export function seasonalCurve(counts, {
|
||||||
|
endWeekBin,
|
||||||
|
binsPerDay = BINS_PER_DAY,
|
||||||
|
recentHalfLife = 7,
|
||||||
|
weekdayHalfLife = 42,
|
||||||
|
shrinkWeeks = 3,
|
||||||
|
} = {}) {
|
||||||
|
const n = counts.length
|
||||||
|
const binsPerWeek = 7 * binsPerDay
|
||||||
|
|
||||||
|
const recentW = new Float64Array(binsPerDay)
|
||||||
|
const recentX = new Float64Array(binsPerDay)
|
||||||
|
const dayW = new Float64Array(binsPerDay)
|
||||||
|
const dayX = new Float64Array(binsPerDay)
|
||||||
|
const weekW = new Float64Array(binsPerWeek)
|
||||||
|
const weekX = new Float64Array(binsPerWeek)
|
||||||
|
const weekW2 = new Float64Array(binsPerWeek)
|
||||||
|
|
||||||
|
for (let i = 0; i < n; i++) {
|
||||||
|
const x = counts[i]
|
||||||
|
if (!Number.isFinite(x)) continue
|
||||||
|
let weekBin = (endWeekBin - n + i) % binsPerWeek
|
||||||
|
if (weekBin < 0) weekBin += binsPerWeek
|
||||||
|
const dayBin = weekBin % binsPerDay
|
||||||
|
const ageDays = (n - 1 - i) / binsPerDay
|
||||||
|
const recent = 2 ** (-ageDays / recentHalfLife)
|
||||||
|
const slow = 2 ** (-ageDays / weekdayHalfLife)
|
||||||
|
recentW[dayBin] += recent
|
||||||
|
recentX[dayBin] += recent * x
|
||||||
|
dayW[dayBin] += slow
|
||||||
|
dayX[dayBin] += slow * x
|
||||||
|
weekW[weekBin] += slow
|
||||||
|
weekX[weekBin] += slow * x
|
||||||
|
weekW2[weekBin] += slow * slow
|
||||||
|
}
|
||||||
|
|
||||||
|
const estimate = new Float64Array(binsPerWeek)
|
||||||
|
for (let wb = 0; wb < binsPerWeek; wb++) {
|
||||||
|
const db = wb % binsPerDay
|
||||||
|
const recentMean = recentW[db] > 0 ? recentX[db] / recentW[db] : NaN
|
||||||
|
const dayMean = dayW[db] > 0 ? dayX[db] / dayW[db] : NaN
|
||||||
|
const weekMean = weekW[wb] > 0 ? weekX[wb] / weekW[wb] : 0
|
||||||
|
const nEff = weekW2[wb] > 0 ? (weekW[wb] * weekW[wb]) / weekW2[wb] : 0
|
||||||
|
const shrink = nEff / (nEff + shrinkWeeks)
|
||||||
|
const base = Number.isFinite(recentMean)
|
||||||
|
? recentMean
|
||||||
|
: Number.isFinite(dayMean) ? dayMean : 0
|
||||||
|
const deviation = Number.isFinite(dayMean) ? weekMean - dayMean : 0
|
||||||
|
estimate[wb] = base + shrink * deviation
|
||||||
|
}
|
||||||
|
return estimate
|
||||||
|
}
|
||||||
|
|
||||||
|
/** Week bin (0 = Monday 00:00–00:05 UTC) containing timestamp t. */
|
||||||
|
export function weekBinIndex(t) {
|
||||||
|
return Math.floor((t - mondayUTC(t)) / MIN5)
|
||||||
|
}
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Typical-week estimate from sparse 5-minute buckets, using history up to
|
||||||
|
* tEnd (default now): bins are densified from the first recorded bucket
|
||||||
|
* (capped at MAX_HISTORY_DAYS back), smoothed with the same Gaussian the
|
||||||
|
* week view uses, then folded by seasonalCurve. Returns BINS_PER_WEEK
|
||||||
|
* counts per 5-minute bin starting Monday, or null when there is less than
|
||||||
|
* a day of history.
|
||||||
|
*/
|
||||||
|
export function typicalWeek(buckets, tEnd = Date.now()) {
|
||||||
|
const raw = rawTimes(buckets)
|
||||||
|
const times = Object.keys(raw).map(Number)
|
||||||
|
if (!times.length) return null
|
||||||
|
const end = Math.floor(tEnd / MIN5) * MIN5
|
||||||
|
const start = Math.max(Math.min(...times), end - MAX_HISTORY_DAYS * DAY)
|
||||||
|
const n = Math.floor((end - start) / MIN5)
|
||||||
|
if (n < BINS_PER_DAY) return null
|
||||||
|
const counts = new Array(n)
|
||||||
|
for (let i = 0; i < n; i++) counts[i] = raw[start + i * MIN5] || 0
|
||||||
|
const smoothed = smooth(counts, 5, 60)
|
||||||
|
return seasonalCurve(smoothed, { endWeekBin: weekBinIndex(end) })
|
||||||
|
}
|
||||||
@@ -3,8 +3,8 @@
|
|||||||
*
|
*
|
||||||
* Raw data comes as sparse 5-minute buckets; the range picks the x window
|
* Raw data comes as sparse 5-minute buckets; the range picks the x window
|
||||||
* and a coarser bucket size to keep point counts sane. The week range is
|
* and a coarser bucket size to keep point counts sane. The week range is
|
||||||
* aligned to Monday 00:00 UTC and overlays previous weeks' curves (fading
|
* aligned to Monday 00:00 UTC; a "typical week" seasonal estimate
|
||||||
* with age), so weekly patterns compare directly.
|
* (seasonal.js) is overlaid on the week and day views by the chart builder.
|
||||||
*/
|
*/
|
||||||
|
|
||||||
export const MIN5 = 5 * 60e3
|
export const MIN5 = 5 * 60e3
|
||||||
@@ -51,25 +51,21 @@ export function sumRange(raw, t0, t1) {
|
|||||||
}
|
}
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* One series per overlaid week: [this week, 1 week ago, ...], at native
|
* The current week at native 5-minute resolution, truncated at the current
|
||||||
* 5-minute resolution, up to 8 weeks back (and only weeks that overlap the
|
* bucket — no fake zeroes drawn for the future. Counts are rates per hour
|
||||||
* recorded data at all). Each older week's timestamps are shifted forward
|
|
||||||
* onto the current week's axis so all curves overlay inside the plot.
|
|
||||||
* The current week is truncated at the current bucket
|
|
||||||
* — no fake zeroes drawn for the future. Counts are rates per hour
|
|
||||||
* (bucket count * 12): a lone visit in a 5-minute bucket reads as "12/h".
|
* (bucket count * 12): a lone visit in a 5-minute bucket reads as "12/h".
|
||||||
* The coarser ranges use per-day rates instead (unitMinutes = 24*60).
|
* The coarser ranges use per-day rates instead (unitMinutes = 24*60).
|
||||||
|
* Previous weeks are no longer overlaid; the "typical week" seasonal
|
||||||
|
* estimate (seasonal.js) takes their place as the history reference.
|
||||||
*/
|
*/
|
||||||
export function weeklySeries(buckets) {
|
export function weeklySeries(buckets) {
|
||||||
const raw = rawTimes(buckets)
|
const raw = rawTimes(buckets)
|
||||||
const times = Object.keys(raw).map(Number)
|
|
||||||
const now = Date.now()
|
const now = Date.now()
|
||||||
const thisMonday = mondayUTC(now)
|
const thisMonday = mondayUTC(now)
|
||||||
if (!times.length) {
|
|
||||||
const points = []
|
const points = []
|
||||||
const end = Math.min(thisMonday + WEEK, Math.floor(now / MIN5) * MIN5 + MIN5)
|
const end = Math.min(thisMonday + WEEK, Math.floor(now / MIN5) * MIN5 + MIN5)
|
||||||
for (let t = thisMonday; t < end; t += MIN5) {
|
for (let t = thisMonday; t < end; t += MIN5) {
|
||||||
points.push({ t, count: 0 })
|
points.push({ t, count: raw[t] || 0 })
|
||||||
}
|
}
|
||||||
return {
|
return {
|
||||||
series: [{ points, label: `Week ${isoWeek(thisMonday)}`, opacity: 1, area: true }],
|
series: [{ points, label: `Week ${isoWeek(thisMonday)}`, opacity: 1, area: true }],
|
||||||
@@ -81,38 +77,6 @@ export function weeklySeries(buckets) {
|
|||||||
unit: 'hour',
|
unit: 'hour',
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
const oldest = Math.min(...times)
|
|
||||||
// Weeks back as far as the data reaches: difference in Monday indices.
|
|
||||||
const available = (thisMonday - mondayUTC(oldest)) / WEEK + 1
|
|
||||||
const count = Math.min(available, 8)
|
|
||||||
const out = []
|
|
||||||
for (let back = 0; back < count; back++) {
|
|
||||||
const start = thisMonday - back * WEEK
|
|
||||||
const end = back === 0
|
|
||||||
? Math.min(start + WEEK, Math.floor(now / MIN5) * MIN5 + MIN5)
|
|
||||||
: start + WEEK
|
|
||||||
const points = []
|
|
||||||
for (let t = start; t < end; t += MIN5) {
|
|
||||||
points.push({ t: t + back * WEEK, count: raw[t] || 0 })
|
|
||||||
}
|
|
||||||
out.push({
|
|
||||||
points,
|
|
||||||
label: `Week ${isoWeek(start)}`,
|
|
||||||
opacity: Math.max(0.15, 1 - back * 0.25),
|
|
||||||
past: back > 0,
|
|
||||||
area: back === 0,
|
|
||||||
})
|
|
||||||
}
|
|
||||||
return {
|
|
||||||
series: out,
|
|
||||||
t0: thisMonday,
|
|
||||||
t1: thisMonday + WEEK,
|
|
||||||
rate: HOUR / MIN5,
|
|
||||||
binMinutes: 5,
|
|
||||||
unitMinutes: 60,
|
|
||||||
unit: 'hour',
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* Rolling window for the non-week ranges (x max = now), counts converted
|
* Rolling window for the non-week ranges (x max = now), counts converted
|
||||||
|
|||||||
@@ -26,6 +26,15 @@
|
|||||||
/* Selection fill for page text and the CodeMirror editors; themes
|
/* Selection fill for page text and the CodeMirror editors; themes
|
||||||
override when the accent tint clashes with accent-colored text. */
|
override when the accent tint clashes with accent-colored text. */
|
||||||
--selection-bg: color-mix(var(--accent) 30%, transparent);
|
--selection-bg: color-mix(var(--accent) 30%, transparent);
|
||||||
|
/* Referer-badge chip in the analytics viewer: a translucent neutral wash,
|
||||||
|
deliberately NOT themed — the chip sits behind transparent favicons, so
|
||||||
|
black-on-transparent and white-on-transparent glyphs must both stay
|
||||||
|
legible on every theme (a slight whitening keeps black glyphs readable
|
||||||
|
on dark bars without a glaring solid-white chip). Being translucent, it
|
||||||
|
takes the page's tone, so its text follows the theme's colors. */
|
||||||
|
--badge-bg: #aaaaaa44;
|
||||||
|
--badge-text: var(--text);
|
||||||
|
--badge-muted: var(--muted);
|
||||||
/* Code highlighting palette, consumed by pygments.css: complete light and
|
/* Code highlighting palette, consumed by pygments.css: complete light and
|
||||||
dark sets (background included), resolved by light-dark() from the
|
dark sets (background included), resolved by light-dark() from the
|
||||||
used color-scheme. A theme picks a set simply by declaring
|
used color-scheme. A theme picks a set simply by declaring
|
||||||
@@ -472,19 +481,20 @@ main {
|
|||||||
container-type: inline-size;
|
container-type: inline-size;
|
||||||
}
|
}
|
||||||
|
|
||||||
/* Child-entry card stacks: a category page (and the content-less category
|
/* Child-entry cards: a category page (and the content-less category
|
||||||
404) lists its published children after the markdown content — one column
|
404) lists its published children after the markdown content — one
|
||||||
per child, the child's whole subtree flattened into the column in menu
|
card per child (a child without a page of its own is represented by
|
||||||
order (see _cards in views.py). The row bleeds to full page width
|
its first leaf page; see _cards in views.py). The row bleeds to full
|
||||||
(div.wide): the columns first grow to fill it, then shrink rather than
|
page width (div.wide): the cards first grow to fill it, then shrink
|
||||||
wrap. Every card has the same fixed 16/10 shape, covered entirely by the
|
rather than wrap. Every card has the same fixed 16/10 shape, covered
|
||||||
|
entirely by the
|
||||||
page's share image (og:image heuristics, as a background — a gradient
|
page's share image (og:image heuristics, as a background — a gradient
|
||||||
placeholder when it has none) with the title overlaid on a translucent
|
placeholder when it has none) with the title overlaid on a translucent
|
||||||
band at the bottom. The card is one <a> holding only phrasing-level
|
band at the bottom. The card is one <a> holding only phrasing-level
|
||||||
spans; the spans lay out as blocks. */
|
spans; the spans lay out as blocks. */
|
||||||
.cards {
|
.cards {
|
||||||
display: flex;
|
display: flex;
|
||||||
/* Stacks stop growing at their cap; center the row in the bleed then. */
|
/* Cards stop growing at their cap; center the row in the bleed then. */
|
||||||
justify-content: center;
|
justify-content: center;
|
||||||
gap: 1.25rem;
|
gap: 1.25rem;
|
||||||
margin-top: 2.5rem;
|
margin-top: 2.5rem;
|
||||||
@@ -493,18 +503,7 @@ main {
|
|||||||
padding-inline: 1.25rem;
|
padding-inline: 1.25rem;
|
||||||
}
|
}
|
||||||
|
|
||||||
.cards .stack {
|
/* Phones: the cards stack vertically instead of shrinking to slivers.
|
||||||
/* Grow to fill the row (up to the cap — full-width rows would make huge
|
|
||||||
cards), shrink (not wrap) when there are too many. */
|
|
||||||
flex: 1 1 0;
|
|
||||||
max-width: 24rem;
|
|
||||||
min-width: 0;
|
|
||||||
display: flex;
|
|
||||||
flex-direction: column;
|
|
||||||
gap: 1.25rem;
|
|
||||||
}
|
|
||||||
|
|
||||||
/* Phones: the columns stack vertically instead of shrinking to slivers.
|
|
||||||
Text-only cards (gradient cover + description) then fit their content —
|
Text-only cards (gradient cover + description) then fit their content —
|
||||||
the fixed 16/10 shape only makes sense for image covers. */
|
the fixed 16/10 shape only makes sense for image covers. */
|
||||||
@media (max-width: 48rem) {
|
@media (max-width: 48rem) {
|
||||||
@@ -518,12 +517,16 @@ main {
|
|||||||
}
|
}
|
||||||
|
|
||||||
.card {
|
.card {
|
||||||
|
/* Grow to fill the row (up to the cap — full-width rows would make huge
|
||||||
|
cards), shrink (not wrap) when there are too many. */
|
||||||
|
flex: 1 1 0;
|
||||||
|
max-width: 24rem;
|
||||||
position: relative;
|
position: relative;
|
||||||
display: flex;
|
display: flex;
|
||||||
flex-direction: column;
|
flex-direction: column;
|
||||||
aspect-ratio: 16 / 10;
|
aspect-ratio: 16 / 10;
|
||||||
/* Allow shrinking below the text's min-content width: without this the
|
/* Allow shrinking below the text's min-content width: without this the
|
||||||
text cards hold their stack wider than the image-only stacks. */
|
text cards hold their row wider than the image-only cards. */
|
||||||
min-width: 0;
|
min-width: 0;
|
||||||
overflow: hidden;
|
overflow: hidden;
|
||||||
border: 1px solid var(--line);
|
border: 1px solid var(--line);
|
||||||
|
|||||||
@@ -628,7 +628,7 @@ import { reconnectPolicy, socketSlot, watchConnecting } from "./reconnect";
|
|||||||
wsQueue.push(msg);
|
wsQueue.push(msg);
|
||||||
}
|
}
|
||||||
|
|
||||||
function ping({ to, fr = currentPath, read = 0 } = {}) {
|
function ping({ to, fr = currentPath, read = 0, lang } = {}) {
|
||||||
// Reading-time updates from the analytics page itself are not tracked
|
// Reading-time updates from the analytics page itself are not tracked
|
||||||
// (/_a is admin machinery; the server would reject the path anyway).
|
// (/_a is admin machinery; the server would reject the path anyway).
|
||||||
if (!to && currentPath === "/_a") return;
|
if (!to && currentPath === "/_a") return;
|
||||||
@@ -637,6 +637,11 @@ import { reconnectPolicy, socketSlot, watchConnecting } from "./reconnect";
|
|||||||
if (to) msg.to = to;
|
if (to) msg.to = to;
|
||||||
const secs = Math.round(read / 1000);
|
const secs = Math.round(read / 1000);
|
||||||
if (secs > 0) msg.read = secs;
|
if (secs > 0) msg.read = secs;
|
||||||
|
// The rendered language: normally the live <html lang>, but a language
|
||||||
|
// switch passes it explicitly — the swap that updates <html> runs inside
|
||||||
|
// the view-transition callback, after the switch ping goes out.
|
||||||
|
lang = lang || document.documentElement.lang;
|
||||||
|
if (lang) msg.lang = lang;
|
||||||
if (!msg.to && !msg.read) return;
|
if (!msg.to && !msg.read) return;
|
||||||
report(msg);
|
report(msg);
|
||||||
}
|
}
|
||||||
@@ -815,6 +820,11 @@ import { reconnectPolicy, socketSlot, watchConnecting } from "./reconnect";
|
|||||||
const y = scrollY; // a language switch is not a navigation: keep scroll
|
const y = scrollY; // a language switch is not a navigation: keep scroll
|
||||||
await load(currentPath, false);
|
await load(currentPath, false);
|
||||||
scrollTo(0, y);
|
scrollTo(0, y);
|
||||||
|
// Log the switch as a trail event in the new language (load() updated
|
||||||
|
// <html lang>, but possibly inside a still-pending view transition, so
|
||||||
|
// pass the tag explicitly): the ping matches the switch's GET
|
||||||
|
// server-side, so it is not misclassified as a crawler hit.
|
||||||
|
ping({ to: currentPath, lang: tag });
|
||||||
});
|
});
|
||||||
|
|
||||||
// --- Fetch navigation ------------------------------------------------
|
// --- Fetch navigation ------------------------------------------------
|
||||||
|
|||||||
@@ -8,11 +8,11 @@
|
|||||||
* - Disables Vite's screen clearing on startup
|
* - Disables Vite's screen clearing on startup
|
||||||
*
|
*
|
||||||
* Options:
|
* Options:
|
||||||
* paths - Array of paths to proxy (default: ["/api"])
|
* paths - Array of paths to proxy (default: ['/api'])
|
||||||
*/
|
*/
|
||||||
|
|
||||||
export default function fastapiVue({ paths = ["/api"] } = {}) {
|
export default function fastapiVue({ paths = ['/api'] } = {}) {
|
||||||
const backendUrl = process.env.PAGERITE_BACKEND_URL || "http://localhost:8210"
|
const backendUrl = process.env.PAGERITE_BACKEND_URL || 'http://localhost:8210'
|
||||||
|
|
||||||
// Build proxy configuration for each path
|
// Build proxy configuration for each path
|
||||||
const proxy = {}
|
const proxy = {}
|
||||||
@@ -25,12 +25,12 @@ export default function fastapiVue({ paths = ["/api"] } = {}) {
|
|||||||
}
|
}
|
||||||
|
|
||||||
return {
|
return {
|
||||||
name: "vite-plugin-fastapi-pagerite",
|
name: 'vite-plugin-fastapi-pagerite',
|
||||||
config: () => ({
|
config: () => ({
|
||||||
clearScreen: false,
|
clearScreen: false,
|
||||||
server: { proxy },
|
server: { proxy },
|
||||||
build: {
|
build: {
|
||||||
outDir: "../pagerite/frontend-build",
|
outDir: '../pagerite/frontend-build',
|
||||||
emptyOutDir: true,
|
emptyOutDir: true,
|
||||||
},
|
},
|
||||||
}),
|
}),
|
||||||
|
|||||||
@@ -5,7 +5,7 @@ import { defineConfig } from 'vite'
|
|||||||
import vue from '@vitejs/plugin-vue'
|
import vue from '@vitejs/plugin-vue'
|
||||||
import vueDevTools from 'vite-plugin-vue-devtools'
|
import vueDevTools from 'vite-plugin-vue-devtools'
|
||||||
|
|
||||||
const backendUrl = process.env.PAGERITE_BACKEND_URL || 'http://localhost:3200'
|
const backendUrl = process.env.PAGERITE_BACKEND_URL || 'http://localhost:8210'
|
||||||
|
|
||||||
// Proxy everything except Vite's own dev-time paths and the backend machinery
|
// Proxy everything except Vite's own dev-time paths and the backend machinery
|
||||||
// to the FastAPI backend in dev. /_api, /_f, /_themes, /_fonts and /_a are
|
// to the FastAPI backend in dev. /_api, /_f, /_themes, /_fonts and /_a are
|
||||||
|
|||||||
+13
-3
@@ -5,12 +5,12 @@ import os
|
|||||||
from pathlib import Path
|
from pathlib import Path
|
||||||
|
|
||||||
import msgspec
|
import msgspec
|
||||||
from fastapi_vue import server
|
from fastapi_vue import env, server
|
||||||
|
|
||||||
from pagerite.config import Config
|
from pagerite.config import Config
|
||||||
|
|
||||||
DEFAULT_PORT = 8100
|
DEFAULT_PORT = 8100
|
||||||
DEVMODE = os.getenv("PAGERITE_DEV") == "1"
|
os.environ["FASTAPI_VUE"] = "PAGERITE"
|
||||||
|
|
||||||
|
|
||||||
def main() -> None:
|
def main() -> None:
|
||||||
@@ -54,7 +54,17 @@ def main() -> None:
|
|||||||
listen=args.listen,
|
listen=args.listen,
|
||||||
default_port=DEFAULT_PORT,
|
default_port=DEFAULT_PORT,
|
||||||
server_header=False,
|
server_header=False,
|
||||||
reload=Path(__file__).parent if DEVMODE else False,
|
reload=Path(__file__).parent if env.dev else False,
|
||||||
|
# Partial log config, merged over uvicorn's default by fastapi-vue:
|
||||||
|
# root prints at WARNING in production / INFO in dev. Keep our own
|
||||||
|
# loggers audible in production, and silence httpx's per-request INFO
|
||||||
|
# (tracking._schedule_favicon_fetch logs its own one-line summary).
|
||||||
|
log_config={
|
||||||
|
"loggers": {
|
||||||
|
"pagerite": {"level": "INFO"},
|
||||||
|
"httpx": {"level": "WARNING"},
|
||||||
|
}
|
||||||
|
},
|
||||||
**run_args,
|
**run_args,
|
||||||
)
|
)
|
||||||
|
|
||||||
|
|||||||
+113
-23
@@ -2,8 +2,9 @@
|
|||||||
|
|
||||||
Raw recording, display-time classification. Every document GET is appended
|
Raw recording, display-time classification. Every document GET is appended
|
||||||
to ``Analytics.gets`` as a raw access-log line (path with query string, true
|
to ``Analytics.gets`` as a raw access-log line (path with query string, true
|
||||||
HTTP status, external referer origin, preload flag) and every pagerite.js
|
HTTP status, external referer origin, preload flag, rendered content
|
||||||
activity message from the /_ws WebSocket is appended to ``Analytics.msgs``
|
language) and every pagerite.js activity message from the /_ws WebSocket is
|
||||||
|
appended to ``Analytics.msgs``
|
||||||
(navigations ``fr`` -> ``to`` and active reading-time updates). Nothing is
|
(navigations ``fr`` -> ``to`` and active reading-time updates). Nothing is
|
||||||
classified when it is recorded: whether a client turns out to be a reader,
|
classified when it is recorded: whether a client turns out to be a reader,
|
||||||
a crawler or a scanner is decided by ``Store.display()`` from the raw
|
a crawler or a scanner is decided by ``Store.display()`` from the raw
|
||||||
@@ -92,6 +93,9 @@ class Ping(msgspec.Struct, omit_defaults=True):
|
|||||||
read: int = 0
|
read: int = 0
|
||||||
#: Admin client: record but hide everything from the statistics.
|
#: Admin client: record but hide everything from the statistics.
|
||||||
hide: bool = False
|
hide: bool = False
|
||||||
|
#: Rendered language of the page the activity happened on (the page's
|
||||||
|
#: ``<html lang>``, sent by pagerite.js).
|
||||||
|
lang: str = ""
|
||||||
|
|
||||||
|
|
||||||
class Get(msgspec.Struct, omit_defaults=True):
|
class Get(msgspec.Struct, omit_defaults=True):
|
||||||
@@ -115,6 +119,9 @@ class Get(msgspec.Struct, omit_defaults=True):
|
|||||||
#: never counted as a view/crawler/abuse hit; recorded only so a later
|
#: never counted as a view/crawler/abuse hit; recorded only so a later
|
||||||
#: cache-served navigation can be attributed this GET's status.
|
#: cache-served navigation can be attributed this GET's status.
|
||||||
pre: bool = False
|
pre: bool = False
|
||||||
|
#: Rendered content language of the served document; "" for
|
||||||
|
#: non-localized responses (404 probes, reserved paths).
|
||||||
|
lang: str = ""
|
||||||
|
|
||||||
|
|
||||||
class Msg(msgspec.Struct, omit_defaults=True):
|
class Msg(msgspec.Struct, omit_defaults=True):
|
||||||
@@ -135,6 +142,9 @@ class Msg(msgspec.Struct, omit_defaults=True):
|
|||||||
to: str = ""
|
to: str = ""
|
||||||
#: Active reading time (seconds) spent on ``fr`` since the last report.
|
#: Active reading time (seconds) spent on ``fr`` since the last report.
|
||||||
read: int = 0
|
read: int = 0
|
||||||
|
#: Rendered language reported by the client for the page the activity
|
||||||
|
#: happened on.
|
||||||
|
lang: str = ""
|
||||||
|
|
||||||
|
|
||||||
class Client(msgspec.Struct, omit_defaults=True):
|
class Client(msgspec.Struct, omit_defaults=True):
|
||||||
@@ -191,6 +201,8 @@ class TrailItem(msgspec.Struct, omit_defaults=True):
|
|||||||
|
|
||||||
``read`` accumulates active reading time (seconds) across the whole
|
``read`` accumulates active reading time (seconds) across the whole
|
||||||
visit; ``status`` is the most recent HTTP status seen for the target.
|
visit; ``status`` is the most recent HTTP status seen for the target.
|
||||||
|
A page seen in two rendered languages within one visit (a mid-article
|
||||||
|
language switch) gets one item per language.
|
||||||
"""
|
"""
|
||||||
|
|
||||||
to: str
|
to: str
|
||||||
@@ -198,6 +210,10 @@ class TrailItem(msgspec.Struct, omit_defaults=True):
|
|||||||
read: int = 0
|
read: int = 0
|
||||||
#: Most recent HTTP status of the response (200 or 404).
|
#: Most recent HTTP status of the response (200 or 404).
|
||||||
status: int = 200
|
status: int = 200
|
||||||
|
#: Rendered language of the target: the client's report, for the entry
|
||||||
|
#: page falling back to its GET's rendered language; "" when unknown
|
||||||
|
#: (old clients or data from before language recording).
|
||||||
|
lang: str = ""
|
||||||
|
|
||||||
|
|
||||||
class Visit(msgspec.Struct, omit_defaults=True):
|
class Visit(msgspec.Struct, omit_defaults=True):
|
||||||
@@ -206,8 +222,9 @@ class Visit(msgspec.Struct, omit_defaults=True):
|
|||||||
``trail`` holds the entry page and everything seen afterwards, keyed by
|
``trail`` holds the entry page and everything seen afterwards, keyed by
|
||||||
the timestamp of first sight (insertion order = first-seen order);
|
the timestamp of first sight (insertion order = first-seen order);
|
||||||
re-visiting an already seen target updates its item instead of
|
re-visiting an already seen target updates its item instead of
|
||||||
appending. Client metadata is held in ``Analytics.clients`` keyed by
|
appending — unless the client reports a different rendered language for
|
||||||
``client``.
|
it, which appends a distinct item (a mid-article language switch).
|
||||||
|
Client metadata is held in ``Analytics.clients`` keyed by ``client``.
|
||||||
"""
|
"""
|
||||||
|
|
||||||
start: datetime
|
start: datetime
|
||||||
@@ -241,6 +258,8 @@ class CrawlerHit(msgspec.Struct, omit_defaults=True):
|
|||||||
query: str = ""
|
query: str = ""
|
||||||
#: HTTP status of the served response (200 or 404 for content pages).
|
#: HTTP status of the served response (200 or 404 for content pages).
|
||||||
status: int = 200
|
status: int = 200
|
||||||
|
#: Rendered content language of the served document (from the GET).
|
||||||
|
lang: str = ""
|
||||||
|
|
||||||
|
|
||||||
class AbuseHit(msgspec.Struct, omit_defaults=True):
|
class AbuseHit(msgspec.Struct, omit_defaults=True):
|
||||||
@@ -319,6 +338,12 @@ class Display(msgspec.Struct, omit_defaults=True):
|
|||||||
views: dict[str, dict[str, int]] = {}
|
views: dict[str, dict[str, int]] = {}
|
||||||
#: New visits per 5-minute bucket: bucket ISO -> count (sparse).
|
#: New visits per 5-minute bucket: bucket ISO -> count (sparse).
|
||||||
site_visits: dict[str, int] = {}
|
site_visits: dict[str, int] = {}
|
||||||
|
#: Site context: true when translation languages are configured, so the
|
||||||
|
#: viewer can suppress language UI on single-language sites.
|
||||||
|
multilingual: bool = False
|
||||||
|
#: The site's primary language (the front page's), so the viewer can
|
||||||
|
#: skip the primary-language default case.
|
||||||
|
primary_lang: str = ""
|
||||||
|
|
||||||
|
|
||||||
def _bucket(now: datetime) -> str:
|
def _bucket(now: datetime) -> str:
|
||||||
@@ -594,22 +619,25 @@ class Store:
|
|||||||
referer: str = "",
|
referer: str = "",
|
||||||
accept_language: str = "",
|
accept_language: str = "",
|
||||||
pre: bool = False,
|
pre: bool = False,
|
||||||
|
lang: str = "",
|
||||||
) -> bytes | None:
|
) -> bytes | None:
|
||||||
"""Append one document GET to the raw log.
|
"""Append one document GET to the raw log.
|
||||||
|
|
||||||
``path`` is the full request path, query string included; ``status``
|
``path`` is the full request path, query string included; ``status``
|
||||||
the true HTTP status of the response; ``referer`` the raw Referer
|
the true HTTP status of the response; ``referer`` the raw Referer
|
||||||
header (reduced here to an external https origin, "" when internal
|
header (reduced here to an external https origin, "" when internal
|
||||||
or absent); ``pre`` marks idle-time preloads from pagerite.js.
|
or absent); ``pre`` marks idle-time preloads from pagerite.js;
|
||||||
|
``lang`` the rendered content language of the served document (""
|
||||||
|
for non-localized responses such as 404 probes and reserved paths).
|
||||||
|
|
||||||
Returns the client hash when the client record was just created (so
|
Returns the client hash when the client record was just created (so
|
||||||
the caller can schedule async enrichment), else None.
|
the caller can schedule async enrichment), else None.
|
||||||
"""
|
"""
|
||||||
lang, country = _parse_accept_language(accept_language)
|
client_lang, country = _parse_accept_language(accept_language)
|
||||||
client_hash = _client_hash(ip, ua, lang)
|
client_hash = _client_hash(ip, ua, client_lang)
|
||||||
new = client_hash not in self.data.clients
|
new = client_hash not in self.data.clients
|
||||||
if new:
|
if new:
|
||||||
self._ensure_client(ip, ua, lang, country=country)
|
self._ensure_client(ip, ua, client_lang, country=country)
|
||||||
self.data.gets.append(
|
self.data.gets.append(
|
||||||
Get(
|
Get(
|
||||||
t=datetime.now(UTC),
|
t=datetime.now(UTC),
|
||||||
@@ -618,6 +646,7 @@ class Store:
|
|||||||
status=status,
|
status=status,
|
||||||
ref=_origin(referer) or "",
|
ref=_origin(referer) or "",
|
||||||
pre=pre,
|
pre=pre,
|
||||||
|
lang=lang,
|
||||||
)
|
)
|
||||||
)
|
)
|
||||||
self._save()
|
self._save()
|
||||||
@@ -632,6 +661,7 @@ class Store:
|
|||||||
accept_language: str = "",
|
accept_language: str = "",
|
||||||
hide: bool = False,
|
hide: bool = False,
|
||||||
read: int = 0,
|
read: int = 0,
|
||||||
|
lang: str = "",
|
||||||
) -> bytes | None:
|
) -> bytes | None:
|
||||||
"""Append one client activity message (``Ping`` from pagerite.js) to
|
"""Append one client activity message (``Ping`` from pagerite.js) to
|
||||||
the raw log.
|
the raw log.
|
||||||
@@ -642,16 +672,18 @@ class Store:
|
|||||||
stored raw and filtered at display time, so future rule changes lose
|
stored raw and filtered at display time, so future rule changes lose
|
||||||
nothing. ``hide`` flags the client record as an admin; the message
|
nothing. ``hide`` flags the client record as an admin; the message
|
||||||
itself is recorded normally and hidden at display time like
|
itself is recorded normally and hidden at display time like
|
||||||
everything else the client ever did.
|
everything else the client ever did. ``lang`` is the rendered
|
||||||
|
language reported by the client for the page the activity happened
|
||||||
|
on.
|
||||||
|
|
||||||
Returns the client hash when the client record was just created (so
|
Returns the client hash when the client record was just created (so
|
||||||
the caller can schedule async enrichment), else None.
|
the caller can schedule async enrichment), else None.
|
||||||
"""
|
"""
|
||||||
lang, country = _parse_accept_language(accept_language)
|
client_lang, country = _parse_accept_language(accept_language)
|
||||||
client_hash = _client_hash(ip, ua, lang)
|
client_hash = _client_hash(ip, ua, client_lang)
|
||||||
new = client_hash not in self.data.clients
|
new = client_hash not in self.data.clients
|
||||||
if new:
|
if new:
|
||||||
self._ensure_client(ip, ua, lang, country=country)
|
self._ensure_client(ip, ua, client_lang, country=country)
|
||||||
if hide:
|
if hide:
|
||||||
self.data.clients[client_hash].hide = True
|
self.data.clients[client_hash].hide = True
|
||||||
fr = (_internal_path(fr) or "") if fr else ""
|
fr = (_internal_path(fr) or "") if fr else ""
|
||||||
@@ -663,7 +695,14 @@ class Store:
|
|||||||
target = _external_target(to) or ""
|
target = _external_target(to) or ""
|
||||||
if target or read > 0:
|
if target or read > 0:
|
||||||
self.data.msgs.append(
|
self.data.msgs.append(
|
||||||
Msg(t=datetime.now(UTC), client=client_hash, fr=fr, to=target, read=read)
|
Msg(
|
||||||
|
t=datetime.now(UTC),
|
||||||
|
client=client_hash,
|
||||||
|
fr=fr,
|
||||||
|
to=target,
|
||||||
|
read=read,
|
||||||
|
lang=lang,
|
||||||
|
)
|
||||||
)
|
)
|
||||||
if target or read > 0 or hide:
|
if target or read > 0 or hide:
|
||||||
self._save()
|
self._save()
|
||||||
@@ -700,7 +739,13 @@ class Store:
|
|||||||
self.data.favicons[origin] = Favicon(file=file, fetched=datetime.now(UTC))
|
self.data.favicons[origin] = Favicon(file=file, fetched=datetime.now(UTC))
|
||||||
self._save()
|
self._save()
|
||||||
|
|
||||||
def display(self, in_menu: Callable[[str], bool] | None = None) -> Display:
|
def display(
|
||||||
|
self,
|
||||||
|
in_menu: Callable[[str], bool] | None = None,
|
||||||
|
*,
|
||||||
|
multilingual: bool = False,
|
||||||
|
primary_lang: str = "",
|
||||||
|
) -> Display:
|
||||||
"""Build the viewer payload from the raw events.
|
"""Build the viewer payload from the raw events.
|
||||||
|
|
||||||
All classification happens here, so the stored data is independent
|
All classification happens here, so the stored data is independent
|
||||||
@@ -722,10 +767,17 @@ class Store:
|
|||||||
- visits: the remaining messages, grouped per client with a new
|
- visits: the remaining messages, grouped per client with a new
|
||||||
visit after ``_SESSION_GAP`` of inactivity. Trail statuses come
|
visit after ``_SESSION_GAP`` of inactivity. Trail statuses come
|
||||||
from the client's GETs (preloads included — a cache-served
|
from the client's GETs (preloads included — a cache-served
|
||||||
navigation's only GET is its preload); the entry referer and UTM
|
navigation's only GET is its preload); trail languages come from
|
||||||
tags from the GET that loaded the entry page.
|
the client's messages (the entry item falling back to its GET's
|
||||||
|
rendered language), and a page re-visited in a different rendered
|
||||||
|
language becomes a distinct trail step. The entry referer and
|
||||||
|
UTM tags come from the GET that loaded the entry page.
|
||||||
|
|
||||||
Hidden (admin) clients are excluded from every list and aggregate.
|
Hidden (admin) clients are excluded from every list and aggregate.
|
||||||
|
``multilingual`` and ``primary_lang`` are site context (translation
|
||||||
|
languages configured, the front page's primary language) copied
|
||||||
|
onto the payload so the viewer can suppress language UI on
|
||||||
|
single-language sites and skip the primary-language default case.
|
||||||
"""
|
"""
|
||||||
in_menu = in_menu or (lambda path: False)
|
in_menu = in_menu or (lambda path: False)
|
||||||
data = self.data
|
data = self.data
|
||||||
@@ -836,7 +888,11 @@ class Store:
|
|||||||
g.path.split("?", 1)[1] if "?" in g.path else ""
|
g.path.split("?", 1)[1] if "?" in g.path else ""
|
||||||
)
|
)
|
||||||
visit.trail[m.t] = TrailItem(
|
visit.trail[m.t] = TrailItem(
|
||||||
to=m.to, status=status_at(h, m.to, m.t)
|
to=m.to,
|
||||||
|
status=status_at(h, m.to, m.t),
|
||||||
|
# The client's report wins; the entry GET fills
|
||||||
|
# in for old clients that don't send lang.
|
||||||
|
lang=m.lang or (g.lang if g is not None else ""),
|
||||||
)
|
)
|
||||||
visits.append(visit)
|
visits.append(visit)
|
||||||
else:
|
else:
|
||||||
@@ -844,18 +900,40 @@ class Store:
|
|||||||
visit.navs[m.t] = Nav(fr=fr, to=m.to)
|
visit.navs[m.t] = Nav(fr=fr, to=m.to)
|
||||||
status = status_at(h, m.to, m.t)
|
status = status_at(h, m.to, m.t)
|
||||||
# First-seen only: repeat pages and repeated exits
|
# First-seen only: repeat pages and repeated exits
|
||||||
# update the existing trail item instead of appending.
|
# update the existing trail item instead of
|
||||||
|
# appending — but a repeat in a different rendered
|
||||||
|
# language (a mid-article language switch) becomes
|
||||||
|
# a distinct step.
|
||||||
for item in visit.trail.values():
|
for item in visit.trail.values():
|
||||||
if item.to == m.to:
|
if item.to == m.to:
|
||||||
|
if m.lang and item.lang and m.lang != item.lang:
|
||||||
|
visit.trail[m.t] = TrailItem(
|
||||||
|
to=m.to, status=status, lang=m.lang
|
||||||
|
)
|
||||||
|
else:
|
||||||
item.status = status
|
item.status = status
|
||||||
|
if not item.lang:
|
||||||
|
item.lang = m.lang
|
||||||
break
|
break
|
||||||
else:
|
else:
|
||||||
visit.trail[m.t] = TrailItem(to=m.to, status=status)
|
visit.trail[m.t] = TrailItem(
|
||||||
|
to=m.to, status=status, lang=m.lang
|
||||||
|
)
|
||||||
if m.read > 0 and m.fr and visit is not None:
|
if m.read > 0 and m.fr and visit is not None:
|
||||||
|
# A page appears in the trail once per language seen:
|
||||||
|
# land the seconds on the matching-language step when
|
||||||
|
# the client reports one, else on the first-seen item.
|
||||||
|
read_item: TrailItem | None = None
|
||||||
for item in visit.trail.values():
|
for item in visit.trail.values():
|
||||||
if item.to == m.fr:
|
if item.to != m.fr:
|
||||||
item.read += m.read
|
continue
|
||||||
|
if read_item is None:
|
||||||
|
read_item = item
|
||||||
|
if m.lang and item.lang == m.lang:
|
||||||
|
read_item = item
|
||||||
break
|
break
|
||||||
|
if read_item is not None:
|
||||||
|
read_item.read += m.read
|
||||||
last_t = m.t
|
last_t = m.t
|
||||||
|
|
||||||
# --- crawler hits: document GETs no message matched
|
# --- crawler hits: document GETs no message matched
|
||||||
@@ -889,6 +967,7 @@ class Store:
|
|||||||
referer=g.ref,
|
referer=g.ref,
|
||||||
query=query,
|
query=query,
|
||||||
status=g.status,
|
status=g.status,
|
||||||
|
lang=g.lang,
|
||||||
)
|
)
|
||||||
)
|
)
|
||||||
|
|
||||||
@@ -912,6 +991,7 @@ class Store:
|
|||||||
referer=visit.referer if first else "",
|
referer=visit.referer if first else "",
|
||||||
query=query if first else "",
|
query=query if first else "",
|
||||||
status=item.status,
|
status=item.status,
|
||||||
|
lang=item.lang,
|
||||||
)
|
)
|
||||||
)
|
)
|
||||||
first = False
|
first = False
|
||||||
@@ -938,6 +1018,8 @@ class Store:
|
|||||||
for origin, f in data.favicons.items()
|
for origin, f in data.favicons.items()
|
||||||
if f.file
|
if f.file
|
||||||
},
|
},
|
||||||
|
multilingual=multilingual,
|
||||||
|
primary_lang=primary_lang,
|
||||||
)
|
)
|
||||||
for visit in kept:
|
for visit in kept:
|
||||||
bucket = _bucket(visit.start)
|
bucket = _bucket(visit.start)
|
||||||
@@ -959,6 +1041,14 @@ class Store:
|
|||||||
nbuckets[nb] = nbuckets.get(nb, 0) + 1
|
nbuckets[nb] = nbuckets.get(nb, 0) + 1
|
||||||
return display
|
return display
|
||||||
|
|
||||||
def display_json(self, in_menu: Callable[[str], bool] | None = None) -> str:
|
def display_json(
|
||||||
|
self,
|
||||||
|
in_menu: Callable[[str], bool] | None = None,
|
||||||
|
*,
|
||||||
|
multilingual: bool = False,
|
||||||
|
primary_lang: str = "",
|
||||||
|
) -> str:
|
||||||
"""The ``display()`` payload as a JSON string for the WebSocket."""
|
"""The ``display()`` payload as a JSON string for the WebSocket."""
|
||||||
return msgspec.json.encode(self.display(in_menu)).decode()
|
return msgspec.json.encode(
|
||||||
|
self.display(in_menu, multilingual=multilingual, primary_lang=primary_lang)
|
||||||
|
).decode()
|
||||||
|
|||||||
+25
-1
@@ -19,6 +19,7 @@ from fastapi import (
|
|||||||
WebSocket,
|
WebSocket,
|
||||||
WebSocketDisconnect,
|
WebSocketDisconnect,
|
||||||
)
|
)
|
||||||
|
from html5tagger import E
|
||||||
from pydantic import BaseModel
|
from pydantic import BaseModel
|
||||||
|
|
||||||
from pagerite import i18n, views
|
from pagerite import i18n, views
|
||||||
@@ -495,6 +496,11 @@ async def editor_ws(ws: WebSocket) -> None:
|
|||||||
markdown = msg.get("markdown", "")
|
markdown = msg.get("markdown", "")
|
||||||
chain = resolve(data.menu, path)
|
chain = resolve(data.menu, path)
|
||||||
node = chain[-1] if chain else None
|
node = chain[-1] if chain else None
|
||||||
|
# Expand {cards} like page_content does, so the preview
|
||||||
|
# shows real cards, not the literal tag. No translation
|
||||||
|
# context: the preview has no lang of its own, so cards
|
||||||
|
# render in their originals.
|
||||||
|
has_cards_tag = views._CARDS_TAG_RE.search(markdown) is not None
|
||||||
rendered = render(
|
rendered = render(
|
||||||
markdown,
|
markdown,
|
||||||
path,
|
path,
|
||||||
@@ -511,12 +517,30 @@ async def editor_ws(ws: WebSocket) -> None:
|
|||||||
if node
|
if node
|
||||||
else None
|
else None
|
||||||
),
|
),
|
||||||
|
directives=(
|
||||||
|
{
|
||||||
|
"cards": lambda args, _env: views._cards_tag(
|
||||||
|
data.menu, data, node, path, args
|
||||||
)
|
)
|
||||||
|
}
|
||||||
|
if node is not None and has_cards_tag
|
||||||
|
else None
|
||||||
|
),
|
||||||
|
)
|
||||||
|
html = rendered.html
|
||||||
|
if node is not None and not has_cards_tag:
|
||||||
|
# Without a {cards} tag page_content appends the
|
||||||
|
# children's cards after the content — the preview
|
||||||
|
# replaces the whole article, so include them here.
|
||||||
|
doc = E.div
|
||||||
|
with doc:
|
||||||
|
views._cards(doc, data.menu, data, node, path)
|
||||||
|
html += str(doc)
|
||||||
await ws.send_json(
|
await ws.send_json(
|
||||||
{
|
{
|
||||||
"type": "html",
|
"type": "html",
|
||||||
"path": path,
|
"path": path,
|
||||||
"html": rendered.html,
|
"html": html,
|
||||||
# Column-layout flag: the preview toggles the
|
# Column-layout flag: the preview toggles the
|
||||||
# article's .multicol class and swaps in the
|
# article's .multicol class and swaps in the
|
||||||
# segmented (.colseg/.cols) article html.
|
# segmented (.colseg/.cols) article html.
|
||||||
|
|||||||
+2
-3
@@ -36,11 +36,10 @@ from pathlib import Path
|
|||||||
|
|
||||||
from fastapi import FastAPI, Request
|
from fastapi import FastAPI, Request
|
||||||
from fastapi.responses import Response
|
from fastapi.responses import Response
|
||||||
from fastapi_vue import Frontend
|
from fastapi_vue import Frontend, env
|
||||||
from starlette.types import ASGIApp, Receive, Scope, Send
|
from starlette.types import ASGIApp, Receive, Scope, Send
|
||||||
|
|
||||||
from pagerite import api, files, pages, tracking
|
from pagerite import api, files, pages, tracking
|
||||||
from pagerite.__main__ import DEVMODE
|
|
||||||
from pagerite.files import file_store
|
from pagerite.files import file_store
|
||||||
from pagerite.state import analytics_store, config, kanta
|
from pagerite.state import analytics_store, config, kanta
|
||||||
|
|
||||||
@@ -99,7 +98,7 @@ async def lifespan(_app: FastAPI) -> AsyncGenerator:
|
|||||||
# is not meant to be browsable by the public anyway.
|
# is not meant to be browsable by the public anyway.
|
||||||
app = FastAPI(
|
app = FastAPI(
|
||||||
title="Pagerite",
|
title="Pagerite",
|
||||||
debug=DEVMODE,
|
debug=env.dev,
|
||||||
lifespan=lifespan,
|
lifespan=lifespan,
|
||||||
docs_url=None,
|
docs_url=None,
|
||||||
redoc_url=None,
|
redoc_url=None,
|
||||||
|
|||||||
+2
-7
@@ -39,10 +39,6 @@ from pagerite.state import (
|
|||||||
|
|
||||||
logger = logging.getLogger(__name__)
|
logger = logging.getLogger(__name__)
|
||||||
|
|
||||||
# mediapreview logs pyvips noise ("VipsForeignSaveJpegTarget argument strip is
|
|
||||||
# deprecated", "threadpool completed with N workers") at INFO; keep warnings.
|
|
||||||
logging.getLogger("mediapreview").setLevel(logging.WARNING)
|
|
||||||
|
|
||||||
router = APIRouter()
|
router = APIRouter()
|
||||||
|
|
||||||
|
|
||||||
@@ -159,14 +155,13 @@ def _svg_to_png(body: bytes, maxsize: int) -> bytes | None:
|
|||||||
|
|
||||||
def _avif_to_format(avif: bytes, suffix: str, quality: int) -> bytes:
|
def _avif_to_format(avif: bytes, suffix: str, quality: int) -> bytes:
|
||||||
"""Re-encode the AVIF derivative into a fallback format (WebP/JPEG)
|
"""Re-encode the AVIF derivative into a fallback format (WebP/JPEG)
|
||||||
via pyvips. JPEG has no alpha, so it is flattened onto white;
|
via pyvips. JPEG has no alpha, so it is flattened onto white."""
|
||||||
``strip`` keeps metadata (EXIF) out of the fallbacks."""
|
|
||||||
import pyvips
|
import pyvips
|
||||||
|
|
||||||
img = pyvips.Image.new_from_buffer(avif, "")
|
img = pyvips.Image.new_from_buffer(avif, "")
|
||||||
if suffix == ".jpg" and img.hasalpha():
|
if suffix == ".jpg" and img.hasalpha():
|
||||||
img = img.flatten(background=[255, 255, 255])
|
img = img.flatten(background=[255, 255, 255])
|
||||||
return img.write_to_buffer(suffix, Q=quality, strip=True)
|
return img.write_to_buffer(suffix, Q=quality, keep="none")
|
||||||
|
|
||||||
|
|
||||||
def _image_derivatives(
|
def _image_derivatives(
|
||||||
|
|||||||
+5
-10
@@ -87,21 +87,16 @@ def select_language(
|
|||||||
|
|
||||||
1. ``?lang=`` wins when a translation exists for it (otherwise falls
|
1. ``?lang=`` wins when a translation exists for it (otherwise falls
|
||||||
through to the header logic).
|
through to the header logic).
|
||||||
2. The original language anywhere in the header list wins — an AI
|
2. Otherwise the first header language that can be served — the
|
||||||
translation is strictly worse than the original for anyone who has
|
original, or one with an available translation.
|
||||||
English configured at all.
|
3. Fall back to the original.
|
||||||
3. Otherwise the first header language with an available translation.
|
|
||||||
4. Fall back to the original.
|
|
||||||
"""
|
"""
|
||||||
if query_lang:
|
if query_lang:
|
||||||
tag = base_tag(query_lang)
|
tag = base_tag(query_lang)
|
||||||
if tag == original or (tag and is_available(tag)):
|
if tag == original or (tag and is_available(tag)):
|
||||||
return tag
|
return tag
|
||||||
langs = parse_accept_language(accept_language or "")
|
for lang in parse_accept_language(accept_language or ""):
|
||||||
if original in langs:
|
if lang == original or is_available(lang):
|
||||||
return original
|
|
||||||
for lang in langs:
|
|
||||||
if lang != original and is_available(lang):
|
|
||||||
return lang
|
return lang
|
||||||
return original
|
return original
|
||||||
|
|
||||||
|
|||||||
+79
-5
@@ -56,9 +56,15 @@ becomes a block `<figure>` — with `<figcaption>` when it has a title.
|
|||||||
Images inline with other content stay plain inline `<img>`, as does raw
|
Images inline with other content stay plain inline `<img>`, as does raw
|
||||||
`<img>` HTML written by the author. Positioning is done with attribute
|
`<img>` HTML written by the author. Positioning is done with attribute
|
||||||
classes, e.g. `{.right}`.
|
classes, e.g. `{.right}`.
|
||||||
|
|
||||||
|
A lone `{name}` or `{name: args}` line is a block directive, expanded by
|
||||||
|
the caller through render(directives=...) — `{dates}` (built in) expands
|
||||||
|
to the article's dateline, `{cards}` / `{cards: path ...}` to card rows
|
||||||
|
of other pages (views.py). Unresolved tags render as the literal source.
|
||||||
"""
|
"""
|
||||||
|
|
||||||
import re
|
import re
|
||||||
|
from collections.abc import Callable
|
||||||
from datetime import datetime, timedelta
|
from datetime import datetime, timedelta
|
||||||
from typing import NamedTuple
|
from typing import NamedTuple
|
||||||
|
|
||||||
@@ -505,6 +511,64 @@ def anchor_ids(text: str, title: str | None = None) -> list[str]:
|
|||||||
]
|
]
|
||||||
|
|
||||||
|
|
||||||
|
#: A lone {...} paragraph: a block directive like {dates} or
|
||||||
|
#: {cards: docs/* news} — name, then optional ":"-separated argument text.
|
||||||
|
_DIRECTIVE_RE = re.compile(r"\{([a-z][a-z0-9_-]*)(?::([^{}\n]*))?\}")
|
||||||
|
|
||||||
|
|
||||||
|
def _directives(state) -> None:
|
||||||
|
"""Turn lone ``{name}`` / ``{name: args}`` paragraphs into directive tokens.
|
||||||
|
|
||||||
|
The expansion is not markdown.py's business: _directive_rule delegates
|
||||||
|
to the resolvers render() put in env["directives"], falling back to the
|
||||||
|
literal source when the tag is unknown in the context (e.g. the editor
|
||||||
|
preview of a page that does not exist yet). The ``cards`` directive gets .wide so it
|
||||||
|
stands alone as a full-width block outside the column segments (the
|
||||||
|
card markup never flows in columns). Runs on the render instance only —
|
||||||
|
the verbatim parser keeps the plain paragraph so segments/chunks see
|
||||||
|
the placeholder source.
|
||||||
|
"""
|
||||||
|
tokens = state.tokens
|
||||||
|
out = []
|
||||||
|
i = 0
|
||||||
|
while i < len(tokens):
|
||||||
|
if (
|
||||||
|
i + 2 < len(tokens)
|
||||||
|
and tokens[i].type == "paragraph_open"
|
||||||
|
and tokens[i + 1].type == "inline"
|
||||||
|
and tokens[i + 2].type == "paragraph_close"
|
||||||
|
):
|
||||||
|
inline = tokens[i + 1]
|
||||||
|
children = inline.children or []
|
||||||
|
if len(children) == 1 and children[0].type == "text":
|
||||||
|
m = _DIRECTIVE_RE.fullmatch(children[0].content.strip())
|
||||||
|
if m:
|
||||||
|
token = Token("directive", "", 0)
|
||||||
|
token.level = tokens[i].level
|
||||||
|
token.map = tokens[i].map
|
||||||
|
token.content = m.group(0)
|
||||||
|
token.meta = {"name": m.group(1), "args": (m.group(2) or "").strip()}
|
||||||
|
if m.group(1) == "cards":
|
||||||
|
token.attrSet("class", "wide")
|
||||||
|
out.append(token)
|
||||||
|
i += 3
|
||||||
|
continue
|
||||||
|
out.append(tokens[i])
|
||||||
|
i += 1
|
||||||
|
state.tokens = out
|
||||||
|
|
||||||
|
|
||||||
|
def _directive_rule(self: RendererHTML, tokens, idx: int, options, env: dict) -> str:
|
||||||
|
"""Render a directive token via env["directives"][name](args, env);
|
||||||
|
unresolved tags render as the literal source paragraph."""
|
||||||
|
token = tokens[idx]
|
||||||
|
resolver = (env.get("directives") or {}).get(token.meta["name"])
|
||||||
|
html = resolver(token.meta["args"], env) if resolver else None
|
||||||
|
if html is None:
|
||||||
|
return f"<p>{escapeHtml(token.content)}</p>\n"
|
||||||
|
return html + "\n"
|
||||||
|
|
||||||
|
|
||||||
def make_md(*, verbatim: bool = False) -> MarkdownIt:
|
def make_md(*, verbatim: bool = False) -> MarkdownIt:
|
||||||
"""A fully configured parser. The module-level ``md`` (below) is the
|
"""A fully configured parser. The module-level ``md`` (below) is the
|
||||||
render instance; ``verbatim=True`` builds the segmentation instance for
|
render instance; ``verbatim=True`` builds the segmentation instance for
|
||||||
@@ -539,6 +603,7 @@ def make_md(*, verbatim: bool = False) -> MarkdownIt:
|
|||||||
)
|
)
|
||||||
parser.add_render_rule("image", _image_rule)
|
parser.add_render_rule("image", _image_rule)
|
||||||
parser.add_render_rule("fence", _fence_rule)
|
parser.add_render_rule("fence", _fence_rule)
|
||||||
|
parser.add_render_rule("directive", _directive_rule)
|
||||||
# GFM alerts (`> [!NOTE]` etc.), built into markdown-it-py's blockquote rule.
|
# GFM alerts (`> [!NOTE]` etc.), built into markdown-it-py's blockquote rule.
|
||||||
parser.options["alerts"] = True
|
parser.options["alerts"] = True
|
||||||
# Block attrs must be stripped before the typographer curlifies their quotes.
|
# Block attrs must be stripped before the typographer curlifies their quotes.
|
||||||
@@ -548,6 +613,8 @@ def make_md(*, verbatim: bool = False) -> MarkdownIt:
|
|||||||
parser.core.ruler.push("tag_task_checkboxes", _tag_task_checkboxes)
|
parser.core.ruler.push("tag_task_checkboxes", _tag_task_checkboxes)
|
||||||
parser.core.ruler.push("shorten_autolinks", _shorten_autolinks)
|
parser.core.ruler.push("shorten_autolinks", _shorten_autolinks)
|
||||||
parser.core.ruler.push("heading_ids", _heading_ids)
|
parser.core.ruler.push("heading_ids", _heading_ids)
|
||||||
|
if not verbatim:
|
||||||
|
parser.core.ruler.push("directives", _directives)
|
||||||
return parser
|
return parser
|
||||||
|
|
||||||
|
|
||||||
@@ -661,6 +728,7 @@ def render(
|
|||||||
modified: datetime | None = None,
|
modified: datetime | None = None,
|
||||||
title: str | None = None,
|
title: str | None = None,
|
||||||
anchors_from: tuple[str, str] | None = None,
|
anchors_from: tuple[str, str] | None = None,
|
||||||
|
directives: dict[str, Callable[[str, dict], str | None]] | None = None,
|
||||||
) -> Rendered:
|
) -> Rendered:
|
||||||
"""Render Markdown text to the article body's HTML and layout flags.
|
"""Render Markdown text to the article body's HTML and layout flags.
|
||||||
|
|
||||||
@@ -682,11 +750,19 @@ def render(
|
|||||||
classes.
|
classes.
|
||||||
|
|
||||||
A ``{dates}`` line expands to the article's published/updated dateline
|
A ``{dates}`` line expands to the article's published/updated dateline
|
||||||
(needs ``created``/``modified``; left as-is in contexts without them,
|
(needs ``created``/``modified``). Block directives in general — a lone
|
||||||
e.g. the editor preview). Position is the author's choice — typically
|
``{name}`` or ``{name: args}`` line — are expanded by the resolvers
|
||||||
|
passed as ``directives`` (name → (args, env) → HTML or None), with
|
||||||
|
``dates`` built in when ``created`` is given; unresolved tags render as
|
||||||
|
the literal source (e.g. in the editor preview of a not-yet-created
|
||||||
|
page).
|
||||||
|
Position is the author's choice — the dateline typically goes
|
||||||
right after the article's h1.
|
right after the article's h1.
|
||||||
"""
|
"""
|
||||||
env = {"page_path": page_path, "line_offset": 0}
|
directives = dict(directives or {})
|
||||||
|
if created is not None:
|
||||||
|
directives.setdefault("dates", lambda _args, _env: _dateline(created, modified))
|
||||||
|
env = {"page_path": page_path, "line_offset": 0, "directives": directives}
|
||||||
if anchors_from is not None:
|
if anchors_from is not None:
|
||||||
env["anchor_ids"] = anchor_ids(*anchors_from)
|
env["anchor_ids"] = anchor_ids(*anchors_from)
|
||||||
if title and not has_h1(text):
|
if title and not has_h1(text):
|
||||||
@@ -732,8 +808,6 @@ def render(
|
|||||||
html = marked
|
html = marked
|
||||||
parts.append(f'<div class="colseg{cols}">{html}</div>')
|
parts.append(f'<div class="colseg{cols}">{html}</div>')
|
||||||
html = "".join(parts)
|
html = "".join(parts)
|
||||||
if created is not None and "<p>{dates}</p>" in html:
|
|
||||||
html = html.replace("<p>{dates}</p>", _dateline(created, modified))
|
|
||||||
return Rendered(html, total > MULTICOL_TEXT)
|
return Rendered(html, total > MULTICOL_TEXT)
|
||||||
|
|
||||||
|
|
||||||
|
|||||||
+4
-3
@@ -152,7 +152,8 @@ async def show_page(request: Request, path: str) -> Response:
|
|||||||
if node is not None and node.published and node.chunks is not None:
|
if node is not None and node.published and node.chunks is not None:
|
||||||
# Language selection (docs/localization.md): ?lang= wins when a
|
# Language selection (docs/localization.md): ?lang= wins when a
|
||||||
# translation exists, else header logic. Analytics keep the raw
|
# translation exists, else header logic. Analytics keep the raw
|
||||||
# Accept-Language header regardless of the selection.
|
# Accept-Language header regardless of the selection, and record
|
||||||
|
# the resolved language as the GET's rendered language.
|
||||||
query_lang = request.query_params.get("lang")
|
query_lang = request.query_params.get("lang")
|
||||||
lang = i18n.select_language(
|
lang = i18n.select_language(
|
||||||
query_lang,
|
query_lang,
|
||||||
@@ -175,7 +176,7 @@ async def show_page(request: Request, path: str) -> Response:
|
|||||||
if request.headers.get("if-none-match") == etag:
|
if request.headers.get("if-none-match") == etag:
|
||||||
return Response(status_code=304)
|
return Response(status_code=304)
|
||||||
if _is_trackable_path(path):
|
if _is_trackable_path(path):
|
||||||
_record_get(request)
|
_record_get(request, lang=lang)
|
||||||
return _html_response(
|
return _html_response(
|
||||||
request,
|
request,
|
||||||
"page",
|
"page",
|
||||||
@@ -205,7 +206,7 @@ async def show_page(request: Request, path: str) -> Response:
|
|||||||
)
|
)
|
||||||
link_lang = i18n.base_tag(query_lang or "")
|
link_lang = i18n.base_tag(query_lang or "")
|
||||||
if _is_trackable_path(path):
|
if _is_trackable_path(path):
|
||||||
_record_get(request, status=404)
|
_record_get(request, status=404, lang=lang)
|
||||||
return _html_response(
|
return _html_response(
|
||||||
request,
|
request,
|
||||||
"category",
|
"category",
|
||||||
|
|||||||
+6
-2
@@ -22,11 +22,11 @@ from pathlib import Path
|
|||||||
import blake3
|
import blake3
|
||||||
from fastapi import HTTPException, Request
|
from fastapi import HTTPException, Request
|
||||||
from fastapi.responses import Response
|
from fastapi.responses import Response
|
||||||
|
from fastapi_vue import env
|
||||||
from kanta import Kanta
|
from kanta import Kanta
|
||||||
from zstandard import ZstdCompressor
|
from zstandard import ZstdCompressor
|
||||||
|
|
||||||
from pagerite import analytics, i18n, seed, translate, views
|
from pagerite import analytics, i18n, seed, translate, views
|
||||||
from pagerite.__main__ import DEVMODE
|
|
||||||
from pagerite.chunks import store_chunks
|
from pagerite.chunks import store_chunks
|
||||||
from pagerite.config import load
|
from pagerite.config import load
|
||||||
from pagerite.data import (
|
from pagerite.data import (
|
||||||
@@ -56,6 +56,10 @@ DB_PATH = os.getenv("PAGERITE_DB", str(SITE_DIR / "content.kantadb"))
|
|||||||
|
|
||||||
# Visit analytics go to their own JSON file, not the kanta database.
|
# Visit analytics go to their own JSON file, not the kanta database.
|
||||||
ANALYTICS_PATH = Path(os.getenv("PAGERITE_ANALYTICS", str(SITE_DIR / "analytics.json")))
|
ANALYTICS_PATH = Path(os.getenv("PAGERITE_ANALYTICS", str(SITE_DIR / "analytics.json")))
|
||||||
|
# The per-hostname data directory may not exist yet on first run; kanta
|
||||||
|
# creates the database file but not its parent directory.
|
||||||
|
Path(DB_PATH).parent.mkdir(parents=True, exist_ok=True)
|
||||||
|
ANALYTICS_PATH.parent.mkdir(parents=True, exist_ok=True)
|
||||||
analytics_store = analytics.Store(ANALYTICS_PATH)
|
analytics_store = analytics.Store(ANALYTICS_PATH)
|
||||||
|
|
||||||
# Content-addressed file store (uploads, seed assets, fetched favicons):
|
# Content-addressed file store (uploads, seed assets, fetched favicons):
|
||||||
@@ -226,7 +230,7 @@ def _html_response(
|
|||||||
# Absolute social/canonical URLs use the site's public origin; on
|
# Absolute social/canonical URLs use the site's public origin; on
|
||||||
# localhost (varying ports) fall back to the request's own base URL.
|
# localhost (varying ports) fall back to the request's own base URL.
|
||||||
base_url = SITE_URL or str(request.base_url).rstrip("/")
|
base_url = SITE_URL or str(request.base_url).rstrip("/")
|
||||||
if DEVMODE:
|
if env.dev:
|
||||||
identity = _render_html(kind, path, base_url, lang, link_lang).encode()
|
identity = _render_html(kind, path, base_url, lang, link_lang).encode()
|
||||||
body = _zstd.compress(identity) if zstd else identity
|
body = _zstd.compress(identity) if zstd else identity
|
||||||
else:
|
else:
|
||||||
|
|||||||
+25
-10
@@ -28,17 +28,13 @@ from fastapi import APIRouter, Request, WebSocket, WebSocketDisconnect
|
|||||||
from fastapi.responses import Response
|
from fastapi.responses import Response
|
||||||
from uarite import uaparse
|
from uarite import uaparse
|
||||||
|
|
||||||
from pagerite import analytics
|
from pagerite import analytics, i18n
|
||||||
from pagerite.data import resolve
|
from pagerite.data import resolve
|
||||||
from pagerite.files import _hash_name, file_store
|
from pagerite.files import _hash_name, file_store
|
||||||
from pagerite.state import SITE_URL, _html_response, analytics_store, data
|
from pagerite.state import SITE_URL, _html_response, analytics_store, data
|
||||||
|
|
||||||
logger = logging.getLogger(__name__)
|
logger = logging.getLogger(__name__)
|
||||||
|
|
||||||
# httpx logs every request at INFO (e.g. the favicon fetches below); our own
|
|
||||||
# one-line summary in _schedule_favicon_fetch replaces that noise.
|
|
||||||
logging.getLogger("httpx").setLevel(logging.WARNING)
|
|
||||||
|
|
||||||
router = APIRouter()
|
router = APIRouter()
|
||||||
|
|
||||||
# Live WebSocket clients for the analytics stream.
|
# Live WebSocket clients for the analytics stream.
|
||||||
@@ -334,7 +330,7 @@ async def _broadcast_analytics() -> None:
|
|||||||
"""Send the current analytics snapshot to every connected WS client."""
|
"""Send the current analytics snapshot to every connected WS client."""
|
||||||
if not _analytics_ws_clients:
|
if not _analytics_ws_clients:
|
||||||
return
|
return
|
||||||
payload = analytics_store.display_json(_in_menu)
|
payload = _display_json()
|
||||||
closed = set()
|
closed = set()
|
||||||
for ws in _analytics_ws_clients:
|
for ws in _analytics_ws_clients:
|
||||||
try:
|
try:
|
||||||
@@ -370,12 +366,29 @@ def _in_menu(path: str) -> bool:
|
|||||||
return resolve(data.menu, path.strip("/")) is not None
|
return resolve(data.menu, path.strip("/")) is not None
|
||||||
|
|
||||||
|
|
||||||
def _record_get(request: Request, *, status: int = 200) -> None:
|
def _display_json() -> str:
|
||||||
|
"""The current analytics snapshot as JSON for the admin stream.
|
||||||
|
|
||||||
|
Adds the site's language context: ``multilingual`` (translation
|
||||||
|
languages configured) lets the viewer suppress language UI on
|
||||||
|
single-language sites, ``primary_lang`` (the front page's) lets it skip
|
||||||
|
the primary-language default case.
|
||||||
|
"""
|
||||||
|
return analytics_store.display_json(
|
||||||
|
_in_menu,
|
||||||
|
multilingual=bool(data.translate_langs),
|
||||||
|
primary_lang=i18n.primary_lang(data.menu, ""),
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
def _record_get(request: Request, *, status: int = 200, lang: str = "") -> None:
|
||||||
"""Record the document GET as one raw access-log line in analytics.
|
"""Record the document GET as one raw access-log line in analytics.
|
||||||
|
|
||||||
Nothing is classified here — the true HTTP status, the full request path
|
Nothing is classified here — the true HTTP status, the full request path
|
||||||
(query included), an external referer origin and the preload flag are
|
(query included), an external referer origin, the preload flag and the
|
||||||
stored, and visitor/crawler/abuse classification happens at display time
|
rendered content language (``lang``, "" for non-localized responses such
|
||||||
|
as 404 probes and reserved paths) are stored, and
|
||||||
|
visitor/crawler/abuse classification happens at display time
|
||||||
(see analytics.Store.display). Idle-time preloads from pagerite.js
|
(see analytics.Store.display). Idle-time preloads from pagerite.js
|
||||||
(``x-pagerite-preload`` header) are recorded with ``pre=True``: never
|
(``x-pagerite-preload`` header) are recorded with ``pre=True``: never
|
||||||
counted, but a navigation later served from the in-memory page cache is
|
counted, but a navigation later served from the in-memory page cache is
|
||||||
@@ -403,6 +416,7 @@ def _record_get(request: Request, *, status: int = 200) -> None:
|
|||||||
referer=referer,
|
referer=referer,
|
||||||
accept_language=request.headers.get("accept-language", ""),
|
accept_language=request.headers.get("accept-language", ""),
|
||||||
pre=bool(request.headers.get("x-pagerite-preload")),
|
pre=bool(request.headers.get("x-pagerite-preload")),
|
||||||
|
lang=lang,
|
||||||
)
|
)
|
||||||
if client_hash is not None:
|
if client_hash is not None:
|
||||||
_schedule_client_enrichment([client_hash])
|
_schedule_client_enrichment([client_hash])
|
||||||
@@ -462,6 +476,7 @@ async def activity_ws(ws: WebSocket) -> None:
|
|||||||
accept_language,
|
accept_language,
|
||||||
hide=msg.hide,
|
hide=msg.hide,
|
||||||
read=msg.read,
|
read=msg.read,
|
||||||
|
lang=msg.lang,
|
||||||
)
|
)
|
||||||
if new_client is not None:
|
if new_client is not None:
|
||||||
_schedule_client_enrichment([new_client])
|
_schedule_client_enrichment([new_client])
|
||||||
@@ -478,7 +493,7 @@ async def analytics_websocket(ws: WebSocket) -> None:
|
|||||||
endpoint. Powers the analytics viewer rendered at /_a.
|
endpoint. Powers the analytics viewer rendered at /_a.
|
||||||
"""
|
"""
|
||||||
await ws.accept()
|
await ws.accept()
|
||||||
await ws.send_text(analytics_store.display_json(_in_menu))
|
await ws.send_text(_display_json())
|
||||||
_analytics_ws_clients.add(ws)
|
_analytics_ws_clients.add(ws)
|
||||||
try:
|
try:
|
||||||
while True:
|
while True:
|
||||||
|
|||||||
+140
-28
@@ -21,6 +21,7 @@ import json
|
|||||||
import os
|
import os
|
||||||
import re
|
import re
|
||||||
|
|
||||||
|
from fastapi_vue import env
|
||||||
from html5tagger import HTML, Document, E, Template
|
from html5tagger import HTML, Document, E, Template
|
||||||
from platformdirs import site_data_dir, user_data_path
|
from platformdirs import site_data_dir, user_data_path
|
||||||
|
|
||||||
@@ -337,7 +338,7 @@ def _layout(
|
|||||||
) -> Template:
|
) -> Template:
|
||||||
"""Page layout template with standard assets and ES-module scripts.
|
"""Page layout template with standard assets and ES-module scripts.
|
||||||
|
|
||||||
In dev (PAGERITE_VITE_URL set) assets are linked from the Vite dev
|
In dev (Vite dev-server URL set) assets are linked from the Vite dev
|
||||||
server and stylesheets use ``blocking="render"`` so the browser waits
|
server and stylesheets use ``blocking="render"`` so the browser waits
|
||||||
for them before showing the page, avoiding a flash of unstyled content.
|
for them before showing the page, avoiding a flash of unstyled content.
|
||||||
In production all page assets are inlined into the document: stylesheets
|
In production all page assets are inlined into the document: stylesheets
|
||||||
@@ -394,7 +395,7 @@ def _layout(
|
|||||||
# dev-server URLs as meta tags (Vite serves the modules and injects
|
# dev-server URLs as meta tags (Vite serves the modules and injects
|
||||||
# their CSS for hot reloads); production inlines all page assets and
|
# their CSS for hot reloads); production inlines all page assets and
|
||||||
# carries the on-demand URLs in one JSON script instead.
|
# carries the on-demand URLs in one JSON script instead.
|
||||||
vite_url = os.environ.get("PAGERITE_VITE_URL")
|
vite_url = env.vite_url
|
||||||
editor_scripts, editor_css = _editor_assets()
|
editor_scripts, editor_css = _editor_assets()
|
||||||
langselect_scripts, langselect_css = _langselect_assets()
|
langselect_scripts, langselect_css = _langselect_assets()
|
||||||
config = {
|
config = {
|
||||||
@@ -790,7 +791,10 @@ def page_content(
|
|||||||
"""Render the contents of the #main element for a page.
|
"""Render the contents of the #main element for a page.
|
||||||
|
|
||||||
A page with published children (a category page) lists them as cards
|
A page with published children (a category page) lists them as cards
|
||||||
after the markdown content. With a translation, its Markdown goes
|
after the markdown content — unless the content has a ``{cards}`` tag,
|
||||||
|
which places card rows itself (bare: the children; with paths:
|
||||||
|
those pages, ``path/*`` their children, ``path/**`` all descendants),
|
||||||
|
one row per tag. With a translation, its Markdown goes
|
||||||
through the same render pipeline; missing pieces (markdown=None, absent
|
through the same render pipeline; missing pieces (markdown=None, absent
|
||||||
title entries) fall back to the original. ``lang`` feeds the cards'
|
title entries) fall back to the original. ``lang`` feeds the cards'
|
||||||
per-target localization.
|
per-target localization.
|
||||||
@@ -812,8 +816,24 @@ def page_content(
|
|||||||
)
|
)
|
||||||
# The title is injected into the markdown (as # title when it has no
|
# The title is injected into the markdown (as # title when it has no
|
||||||
# h1 of its own), so title and content render as one article.
|
# h1 of its own), so title and content render as one article.
|
||||||
|
# A {cards} tag places the card rows itself (possibly several);
|
||||||
|
# without one the children are appended after the content as before.
|
||||||
|
has_cards_tag = _CARDS_TAG_RE.search(content) is not None
|
||||||
|
directives = None
|
||||||
|
if has_cards_tag:
|
||||||
|
directives = {
|
||||||
|
"cards": lambda args, _env: _cards_tag(
|
||||||
|
menu, data, node, path, args, translation, link_lang, lang
|
||||||
|
)
|
||||||
|
}
|
||||||
rendered = render(
|
rendered = render(
|
||||||
content, path, node.created, node.modified, title=title, anchors_from=anchors_from
|
content,
|
||||||
|
path,
|
||||||
|
node.created,
|
||||||
|
node.modified,
|
||||||
|
title=title,
|
||||||
|
anchors_from=anchors_from,
|
||||||
|
directives=directives,
|
||||||
)
|
)
|
||||||
# Long articles get .multicol: the article column cap lifts (see the
|
# Long articles get .multicol: the article column cap lifts (see the
|
||||||
# #content grid in pagerite.css) and the .cols segments lay out in at
|
# #content grid in pagerite.css) and the .cols segments lay out in at
|
||||||
@@ -822,10 +842,25 @@ def page_content(
|
|||||||
doc = E.article(class_="multicol") if rendered.multicol else E.article
|
doc = E.article(class_="multicol") if rendered.multicol else E.article
|
||||||
with doc:
|
with doc:
|
||||||
doc(HTML(rendered.html))
|
doc(HTML(rendered.html))
|
||||||
|
if not has_cards_tag:
|
||||||
_cards(doc, menu, data, node, path, translation, link_lang, lang)
|
_cards(doc, menu, data, node, path, translation, link_lang, lang)
|
||||||
return HTML(str(doc))
|
return HTML(str(doc))
|
||||||
|
|
||||||
|
|
||||||
|
def _represent(node: Node, path: str) -> tuple[str, Node] | None:
|
||||||
|
"""The (path, node) a card for this menu item points at: the item
|
||||||
|
itself when it has a page, else its first published leaf page,
|
||||||
|
recursively — the same logic as nav links (first_leaf)."""
|
||||||
|
if node.chunks:
|
||||||
|
return path, node
|
||||||
|
for slug, child in sorted_nodes(node.children):
|
||||||
|
if child.published:
|
||||||
|
cpath = f"{path}/{slug}" if path else slug
|
||||||
|
if r := _represent(child, cpath):
|
||||||
|
return r
|
||||||
|
return None
|
||||||
|
|
||||||
|
|
||||||
def _cards(
|
def _cards(
|
||||||
doc,
|
doc,
|
||||||
menu: dict[str, Node],
|
menu: dict[str, Node],
|
||||||
@@ -836,38 +871,107 @@ def _cards(
|
|||||||
link_lang: str = "",
|
link_lang: str = "",
|
||||||
lang: str = "",
|
lang: str = "",
|
||||||
) -> None:
|
) -> None:
|
||||||
"""Card stacks of the node's published children (nothing when childless).
|
"""Cards of the node's published children (nothing when childless).
|
||||||
|
|
||||||
One column per direct child, all in a single full-width row (the .wide
|
One card per direct child, all in a single full-width row (the .wide
|
||||||
breakout): the columns grow to fill the page and shrink rather than
|
breakout): the cards grow to fill the page and shrink rather than
|
||||||
wrap. A column holds the child's whole subtree flattened in menu order
|
wrap. A child without a page of its own is represented by its first
|
||||||
— nesting levels are not split out — starting with the first page that
|
leaf page (_represent, the nav-link logic). Each card is one <a>
|
||||||
has actual content (the child itself when it does, its first leaf
|
showing the page's share
|
||||||
otherwise, recursively). Each card is one <a> showing the page's share
|
|
||||||
image (the same heuristics as og:image) as the cover and its title;
|
image (the same heuristics as og:image) as the cover and its title;
|
||||||
image-less cards get a gradient cover and also show the description.
|
image-less cards get a gradient cover and also show the description.
|
||||||
Only phrasing-level elements (spans) go inside the <a>: as a formatting
|
Only phrasing-level elements (spans) go inside the <a>: as a formatting
|
||||||
element it would be cloned by the HTML parser around any block-level
|
element it would be cloned by the HTML parser around any block-level
|
||||||
child, splitting one card into several links.
|
child, splitting one card into several links.
|
||||||
"""
|
"""
|
||||||
items = [(s, c) for s, c in sorted_nodes(node.children) if c.published]
|
items = [
|
||||||
|
r
|
||||||
|
for s, c in sorted_nodes(node.children)
|
||||||
|
if c.published
|
||||||
|
for r in [_represent(c, f"{path}/{s}" if path else s)]
|
||||||
|
if r
|
||||||
|
]
|
||||||
if not items:
|
if not items:
|
||||||
return
|
return
|
||||||
with doc.div(class_="cards wide"):
|
with doc.div(class_="cards wide"):
|
||||||
for slug, child in items:
|
for cpath, cnode in items:
|
||||||
cpath = f"{path}/{slug}" if path else slug
|
_card(doc, data, cnode, cpath, translation, link_lang, lang)
|
||||||
entries = list(_walk(child, cpath))
|
|
||||||
if not entries:
|
|
||||||
continue
|
#: A lone {cards} or {cards: ...} line in the markdown: card rows placed
|
||||||
with doc.div(class_="stack"):
|
#: by the author. Any such tag suppresses the automatic end-of-page cards.
|
||||||
for epath, enode in entries:
|
_CARDS_TAG_RE = re.compile(r"^\{cards(?::[^{}\n]*)?\}[ \t]*$", re.M)
|
||||||
_card(doc, data, enode, epath, translation, link_lang, lang)
|
|
||||||
|
|
||||||
|
def _cards_tag(
|
||||||
|
menu: dict[str, Node],
|
||||||
|
data: Data,
|
||||||
|
node: Node,
|
||||||
|
path: str,
|
||||||
|
args: str,
|
||||||
|
translation: Translation | None = None,
|
||||||
|
link_lang: str = "",
|
||||||
|
lang: str = "",
|
||||||
|
) -> str:
|
||||||
|
"""Expand a ``{cards}`` directive to a card row (the same markup as
|
||||||
|
_cards, so author-placed cards look like category cards).
|
||||||
|
|
||||||
|
A bare ``{cards}`` lists the page's own published children — what
|
||||||
|
page_content appends when the tag is absent — or, on the front page,
|
||||||
|
the other top-level pages (the front page is a top-level item itself,
|
||||||
|
not the parent of the others). Arguments are space-separated page
|
||||||
|
paths: a plain path renders that page alone (never its children),
|
||||||
|
``path/*`` its published children and ``path/**`` all published
|
||||||
|
descendant pages. One card per item; a page-less item is represented
|
||||||
|
by its first leaf page (_represent). Unresolvable paths are skipped;
|
||||||
|
a tag that ends up with nothing renders as nothing.
|
||||||
|
"""
|
||||||
|
items: list[tuple[str, Node]] = []
|
||||||
|
specs = args.split()
|
||||||
|
|
||||||
|
def children(base: str, parent: Node):
|
||||||
|
for s, c in sorted_nodes(parent.children):
|
||||||
|
if c.published:
|
||||||
|
if r := _represent(c, f"{base}/{s}" if base else s):
|
||||||
|
items.append(r)
|
||||||
|
|
||||||
|
if not specs:
|
||||||
|
if path:
|
||||||
|
children(path, node)
|
||||||
|
else:
|
||||||
|
for s, c in sorted_nodes(menu):
|
||||||
|
if c.published and s:
|
||||||
|
if r := _represent(c, s):
|
||||||
|
items.append(r)
|
||||||
|
else:
|
||||||
|
for spec in specs:
|
||||||
|
spec = spec.strip("/")
|
||||||
|
if spec.endswith("/**"):
|
||||||
|
base = spec[:-3].rstrip("/")
|
||||||
|
if chain := resolve(menu, base):
|
||||||
|
for s, c in sorted_nodes(chain[-1].children):
|
||||||
|
if c.published:
|
||||||
|
items.extend(_walk(c, f"{base}/{s}" if base else s))
|
||||||
|
elif spec.endswith("/*"):
|
||||||
|
base = spec[:-2].rstrip("/")
|
||||||
|
if chain := resolve(menu, base):
|
||||||
|
children(base, chain[-1])
|
||||||
|
elif chain := resolve(menu, spec):
|
||||||
|
if r := _represent(chain[-1], spec):
|
||||||
|
items.append(r)
|
||||||
|
if not items:
|
||||||
|
return ""
|
||||||
|
doc = E.div(class_="cards wide")
|
||||||
|
with doc:
|
||||||
|
for cpath, cnode in items:
|
||||||
|
_card(doc, data, cnode, cpath, translation, link_lang, lang)
|
||||||
|
return str(doc)
|
||||||
|
|
||||||
|
|
||||||
def _walk(node: Node, path: str):
|
def _walk(node: Node, path: str):
|
||||||
"""Published content pages of a subtree, pre-order in menu order: the
|
"""Published content pages of a subtree, pre-order in menu order: the
|
||||||
node itself first when it has content (the stack's landing card), then
|
node itself first when it has content, then its descendants
|
||||||
its descendants (content-less nodes contribute only their subtree)."""
|
(content-less nodes contribute only their subtree)."""
|
||||||
if node.chunks:
|
if node.chunks:
|
||||||
yield path, node
|
yield path, node
|
||||||
for slug, child in sorted_nodes(node.children):
|
for slug, child in sorted_nodes(node.children):
|
||||||
@@ -884,7 +988,7 @@ def _card(
|
|||||||
link_lang: str = "",
|
link_lang: str = "",
|
||||||
lang: str = "",
|
lang: str = "",
|
||||||
) -> None:
|
) -> None:
|
||||||
"""One card in a stack: cover + title, plus the description when the
|
"""One card: cover + title, plus the description when the
|
||||||
page has no image (its card shows a gradient cover instead).
|
page has no image (its card shows a gradient cover instead).
|
||||||
|
|
||||||
The card text localizes per target article where that page is
|
The card text localizes per target article where that page is
|
||||||
@@ -897,7 +1001,15 @@ def _card(
|
|||||||
md = node_markdown(data, node) or ""
|
md = node_markdown(data, node) or ""
|
||||||
if lang and lang in node.langs:
|
if lang and lang in node.langs:
|
||||||
md = i18n.hybrid_markdown(data, node, path, lang)
|
md = i18n.hybrid_markdown(data, node, path, lang)
|
||||||
html = render(md, path, node.created, node.modified).html
|
html = render(
|
||||||
|
md,
|
||||||
|
path,
|
||||||
|
node.created,
|
||||||
|
node.modified,
|
||||||
|
# Card heuristics only mine the prose: nested {cards} rows
|
||||||
|
# would just be noise in the description extraction.
|
||||||
|
directives={"cards": lambda _args, _env: ""},
|
||||||
|
).html
|
||||||
image, _ = _media(html)
|
image, _ = _media(html)
|
||||||
if not image:
|
if not image:
|
||||||
description = _description(html, 150)
|
description = _description(html, 150)
|
||||||
@@ -1226,7 +1338,7 @@ def _page_assets() -> tuple[list[str], list[str]]:
|
|||||||
by the entry (e.g. overlayscrollbars.css) is extracted by Vite and must
|
by the entry (e.g. overlayscrollbars.css) is extracted by Vite and must
|
||||||
be linked separately.
|
be linked separately.
|
||||||
"""
|
"""
|
||||||
vite_url = os.environ.get("PAGERITE_VITE_URL")
|
vite_url = env.vite_url
|
||||||
if vite_url:
|
if vite_url:
|
||||||
return [f"{vite_url}/src/pagerite.js"], []
|
return [f"{vite_url}/src/pagerite.js"], []
|
||||||
if "page" not in _asset_cache:
|
if "page" not in _asset_cache:
|
||||||
@@ -1244,7 +1356,7 @@ def _editor_assets() -> tuple[list[str], str | None]:
|
|||||||
The shared CSS is already linked on the page, so the pen only needs the
|
The shared CSS is already linked on the page, so the pen only needs the
|
||||||
editor-specific stylesheet.
|
editor-specific stylesheet.
|
||||||
"""
|
"""
|
||||||
vite_url = os.environ.get("PAGERITE_VITE_URL")
|
vite_url = env.vite_url
|
||||||
if vite_url:
|
if vite_url:
|
||||||
return [f"{vite_url}/@vite/client", f"{vite_url}/src/main.js"], None
|
return [f"{vite_url}/@vite/client", f"{vite_url}/src/main.js"], None
|
||||||
if "editor" not in _asset_cache:
|
if "editor" not in _asset_cache:
|
||||||
@@ -1256,7 +1368,7 @@ def _editor_assets() -> tuple[list[str], str | None]:
|
|||||||
|
|
||||||
def _analytics_assets() -> tuple[list[str], list[str]]:
|
def _analytics_assets() -> tuple[list[str], list[str]]:
|
||||||
"""Script and stylesheet URLs for the analytics page entry."""
|
"""Script and stylesheet URLs for the analytics page entry."""
|
||||||
vite_url = os.environ.get("PAGERITE_VITE_URL")
|
vite_url = env.vite_url
|
||||||
if vite_url:
|
if vite_url:
|
||||||
return [f"{vite_url}/src/analytics-main.js"], []
|
return [f"{vite_url}/src/analytics-main.js"], []
|
||||||
if "analytics" not in _asset_cache:
|
if "analytics" not in _asset_cache:
|
||||||
@@ -1270,7 +1382,7 @@ def _analytics_assets() -> tuple[list[str], list[str]]:
|
|||||||
|
|
||||||
def _langselect_assets() -> tuple[list[str], list[str]]:
|
def _langselect_assets() -> tuple[list[str], list[str]]:
|
||||||
"""Script and stylesheet URLs for the on-demand public language selector."""
|
"""Script and stylesheet URLs for the on-demand public language selector."""
|
||||||
vite_url = os.environ.get("PAGERITE_VITE_URL")
|
vite_url = env.vite_url
|
||||||
if vite_url:
|
if vite_url:
|
||||||
return [f"{vite_url}/src/langselect-main.js"], []
|
return [f"{vite_url}/src/langselect-main.js"], []
|
||||||
if "langselect" not in _asset_cache:
|
if "langselect" not in _asset_cache:
|
||||||
|
|||||||
+3
-3
@@ -17,15 +17,15 @@ readme = "README.md"
|
|||||||
requires-python = ">=3.14"
|
requires-python = ">=3.14"
|
||||||
dependencies = [
|
dependencies = [
|
||||||
"blake3>=1.0.9",
|
"blake3>=1.0.9",
|
||||||
"fastapi-vue~=1.4.2",
|
"fastapi-vue~=1.7.2",
|
||||||
"fastapi[standard]>=0.141.1",
|
"fastapi[standard]>=0.141.1",
|
||||||
"html5tagger>=2.0.0",
|
"html5tagger>=2.0.0",
|
||||||
"httpx>=0.28.1",
|
"httpx>=0.28.1",
|
||||||
"kanta>=0.9.0",
|
"kanta>=0.9.2",
|
||||||
"markdown-it-py>=4.2.0",
|
"markdown-it-py>=4.2.0",
|
||||||
"maxminddb>=3.1.1",
|
"maxminddb>=3.1.1",
|
||||||
"mdit-py-plugins>=0.6.1",
|
"mdit-py-plugins>=0.6.1",
|
||||||
"mediapreview[standard]>=0.2.3",
|
"mediapreview[standard]>=0.2.5",
|
||||||
"platformdirs>=4.11.5",
|
"platformdirs>=4.11.5",
|
||||||
"pygments>=2.20.0",
|
"pygments>=2.20.0",
|
||||||
"python-slugify>=8.0.4",
|
"python-slugify>=8.0.4",
|
||||||
|
|||||||
+10
-5
@@ -1,11 +1,12 @@
|
|||||||
#!/usr/bin/env -S uv run
|
#!/usr/bin/env -S uv run
|
||||||
|
# auto-upgrade@fastapi-vue-setup - remove this if you modify this file
|
||||||
"""Run Vite development server for Vue app and FastAPI backend with auto-reload."""
|
"""Run Vite development server for Vue app and FastAPI backend with auto-reload."""
|
||||||
|
|
||||||
import argparse
|
import argparse
|
||||||
import asyncio
|
import asyncio
|
||||||
import os
|
import os
|
||||||
|
import subprocess
|
||||||
import sys
|
import sys
|
||||||
from contextlib import suppress
|
|
||||||
from pathlib import Path
|
from pathlib import Path
|
||||||
|
|
||||||
import tracerite
|
import tracerite
|
||||||
@@ -47,11 +48,11 @@ async def run_devserver(
|
|||||||
os.environ["PAGERITE_DEV"] = "1"
|
os.environ["PAGERITE_DEV"] = "1"
|
||||||
|
|
||||||
async with ProcessGroup() as pg:
|
async with ProcessGroup() as pg:
|
||||||
|
pg.create_task(check_ports_free(viteurl, backurl))
|
||||||
npm_i = await pg.spawn(*npm_install, cwd=front)
|
npm_i = await pg.spawn(*npm_install, cwd=front)
|
||||||
await check_ports_free(viteurl, backurl)
|
await pg.spawn(*pagerite, *(extra_args or []), vital=True)
|
||||||
await pg.spawn(*pagerite, *(extra_args or []))
|
|
||||||
await pg.wait(npm_i, ready(backurl, path=HEALTH))
|
await pg.wait(npm_i, ready(backurl, path=HEALTH))
|
||||||
await pg.spawn(*vite, cwd=front)
|
await pg.spawn(*vite, cwd=front, vital=True)
|
||||||
|
|
||||||
|
|
||||||
def main() -> None:
|
def main() -> None:
|
||||||
@@ -74,8 +75,12 @@ def main() -> None:
|
|||||||
help=f"FastAPI (default: localhost:{DEFAULT_DEV_PORT})",
|
help=f"FastAPI (default: localhost:{DEFAULT_DEV_PORT})",
|
||||||
)
|
)
|
||||||
args, extra_args = parser.parse_known_args()
|
args, extra_args = parser.parse_known_args()
|
||||||
with suppress(KeyboardInterrupt):
|
try:
|
||||||
asyncio.run(run_devserver(args.listen, args.backend, extra_args))
|
asyncio.run(run_devserver(args.listen, args.backend, extra_args))
|
||||||
|
except* KeyboardInterrupt:
|
||||||
|
pass # user stopped the devserver: normal exit
|
||||||
|
except* subprocess.SubprocessError, RuntimeError:
|
||||||
|
raise SystemExit(1) from None # logged in devutil already; exit 1
|
||||||
|
|
||||||
|
|
||||||
HELP_EPILOG = """
|
HELP_EPILOG = """
|
||||||
|
|||||||
@@ -11,20 +11,27 @@ from pathlib import Path
|
|||||||
MIN_NODE_VERSION = 20
|
MIN_NODE_VERSION = 20
|
||||||
|
|
||||||
|
|
||||||
class _PrefixFormatter(logging.Formatter):
|
class _Formatter(logging.Formatter):
|
||||||
"""Formatter that adds prefix based on log level."""
|
"""Prefix formatter, intentionally different from fastapi_vue.logging.
|
||||||
|
|
||||||
|
INFO and below pass through unprefixed so messages can use their own
|
||||||
|
markings (>>>, ###); WARNING and above get an emoji prefix.
|
||||||
|
"""
|
||||||
|
|
||||||
def format(self, record: logging.LogRecord) -> str:
|
def format(self, record: logging.LogRecord) -> str:
|
||||||
|
if record.levelno >= logging.ERROR:
|
||||||
|
return f"🛑 {record.getMessage()}"
|
||||||
if record.levelno >= logging.WARNING:
|
if record.levelno >= logging.WARNING:
|
||||||
return f"⚠️ {record.getMessage()}"
|
return f"💣 {record.getMessage()}"
|
||||||
return record.getMessage()
|
return record.getMessage()
|
||||||
|
|
||||||
|
|
||||||
_handler = logging.StreamHandler()
|
_handler = logging.StreamHandler()
|
||||||
_handler.setFormatter(_PrefixFormatter())
|
_handler.setFormatter(_Formatter())
|
||||||
logger = logging.getLogger("fastapi-vue")
|
logger = logging.getLogger("fastapi-vue")
|
||||||
logger.addHandler(_handler)
|
logger.addHandler(_handler)
|
||||||
logger.setLevel(logging.INFO)
|
logger.setLevel(logging.INFO)
|
||||||
|
logger.propagate = False # own handler; do not double-print via a configured root
|
||||||
|
|
||||||
|
|
||||||
def _check_node_version(node_path: str) -> None:
|
def _check_node_version(node_path: str) -> None:
|
||||||
|
|||||||
@@ -1,108 +1,87 @@
|
|||||||
# ruff: noqa: INP001
|
# ruff: noqa: INP001
|
||||||
"""Utilities meant for devserver script, used only in source repository with dev deps."""
|
"""Utilities meant for devserver script, used only in source repository with dev deps."""
|
||||||
|
|
||||||
|
from __future__ import annotations
|
||||||
|
|
||||||
import asyncio
|
import asyncio
|
||||||
import subprocess
|
|
||||||
import sys
|
import sys
|
||||||
|
from asyncio.subprocess import Process
|
||||||
from contextlib import suppress
|
from contextlib import suppress
|
||||||
from pathlib import Path
|
from pathlib import Path
|
||||||
from typing import TYPE_CHECKING, Any, Self
|
from subprocess import CalledProcessError
|
||||||
|
from typing import TYPE_CHECKING, Any
|
||||||
from urllib.parse import urlsplit
|
from urllib.parse import urlsplit
|
||||||
|
|
||||||
from buildutil import find_dev_tool, find_install_tool, logger
|
from buildutil import find_dev_tool, find_install_tool, logger
|
||||||
from fastapi_vue.hostutil import parse_endpoint
|
from fastapi_vue.hostutil import parse_endpoint
|
||||||
|
|
||||||
if TYPE_CHECKING:
|
if TYPE_CHECKING:
|
||||||
from collections.abc import Coroutine
|
from collections.abc import Awaitable
|
||||||
|
|
||||||
|
|
||||||
class ProcessGroup:
|
class ProcessGroup(asyncio.TaskGroup):
|
||||||
"""Manage async subprocesses with automatic cleanup, like TaskGroup for processes."""
|
"""TaskGroup with structured ownership of async subprocesses."""
|
||||||
|
|
||||||
def __init__(self) -> None:
|
def __init__(self, *, terminate_timeout: float = 10) -> None:
|
||||||
"""Initialize empty process tracking."""
|
"""Set the grace period before terminate() escalates to kill()."""
|
||||||
self._procs: list[asyncio.subprocess.Process] = []
|
super().__init__()
|
||||||
self._cmds: dict[int, str] = {} # pid -> command name
|
self._terminate_timeout = terminate_timeout
|
||||||
|
self._cmds: dict[Process, tuple[str, ...]] = {}
|
||||||
|
|
||||||
async def spawn(
|
async def spawn(
|
||||||
self,
|
self, *cmd: str, cwd: str | None = None, vital: bool = False
|
||||||
*cmd: str,
|
) -> Process:
|
||||||
cwd: str | None = None,
|
"""Spawn and own a subprocess. If a vital process exits, the group cancels."""
|
||||||
) -> asyncio.subprocess.Process:
|
|
||||||
"""Spawn a subprocess and track it."""
|
|
||||||
cmd_name = Path(cmd[0]).stem
|
|
||||||
logger.info(">>> %s", " ".join([cmd_name, *cmd[1:]]))
|
|
||||||
proc = await asyncio.create_subprocess_exec(*cmd, cwd=cwd)
|
|
||||||
self._procs.append(proc)
|
|
||||||
self._cmds[proc.pid] = cmd_name
|
|
||||||
return proc
|
|
||||||
|
|
||||||
async def wait(
|
async def run() -> None:
|
||||||
self,
|
name = Path(cmd[0]).stem
|
||||||
*waitables: "asyncio.subprocess.Process | Coroutine[Any, Any, Any]",
|
logger.info(">>> %s", " ".join([name, *cmd[1:]]))
|
||||||
) -> None:
|
|
||||||
"""Wait for processes/coroutines to complete, raise SystemExit on failure."""
|
|
||||||
|
|
||||||
async def wait_proc(proc: asyncio.subprocess.Process) -> None:
|
|
||||||
returncode = await proc.wait()
|
|
||||||
if returncode != 0:
|
|
||||||
cmd_name = self._cmds.get(proc.pid, "unknown")
|
|
||||||
raise subprocess.CalledProcessError(returncode, cmd_name)
|
|
||||||
|
|
||||||
tasks = [
|
|
||||||
wait_proc(w) if isinstance(w, asyncio.subprocess.Process) else w
|
|
||||||
for w in waitables
|
|
||||||
]
|
|
||||||
try:
|
try:
|
||||||
await asyncio.gather(*tasks)
|
proc = await asyncio.create_subprocess_exec(*cmd, cwd=cwd)
|
||||||
except subprocess.CalledProcessError as e:
|
self._cmds[proc] = cmd
|
||||||
logger.warning("%s failed with exit status %d", e.cmd, e.returncode)
|
started.set_result(proc)
|
||||||
raise SystemExit(1) from None
|
except Exception as e: # noqa: BLE001
|
||||||
|
started.set_exception(e)
|
||||||
async def __aenter__(self) -> Self:
|
|
||||||
"""Enter the async context manager."""
|
|
||||||
return self
|
|
||||||
|
|
||||||
async def __aexit__(self, exc_type: type[BaseException] | None, *_: object) -> None:
|
|
||||||
"""Wait for one process to exit, terminate others, then wait for all."""
|
|
||||||
await self._cleanup(immediate=exc_type is not None)
|
|
||||||
|
|
||||||
async def _cleanup(self, *, immediate: bool = False) -> None:
|
|
||||||
running = [p for p in self._procs if p.returncode is None]
|
|
||||||
if not running:
|
|
||||||
return
|
return
|
||||||
|
|
||||||
if not immediate:
|
|
||||||
# Wait for any one process to exit
|
|
||||||
with suppress(asyncio.CancelledError):
|
|
||||||
await asyncio.wait(
|
|
||||||
[asyncio.create_task(p.wait()) for p in running],
|
|
||||||
return_when=asyncio.FIRST_COMPLETED,
|
|
||||||
)
|
|
||||||
|
|
||||||
# Terminate remaining processes
|
|
||||||
for p in self._procs:
|
|
||||||
if p.returncode is None:
|
|
||||||
with suppress(ProcessLookupError):
|
|
||||||
p.terminate()
|
|
||||||
|
|
||||||
# Wait for all to finish (with overall timeout), shielded from cancellation
|
|
||||||
still_running = [p for p in self._procs if p.returncode is None]
|
|
||||||
if still_running:
|
|
||||||
with suppress(asyncio.CancelledError):
|
|
||||||
try:
|
try:
|
||||||
await asyncio.shield(
|
returncode = await proc.wait()
|
||||||
asyncio.wait_for(
|
finally:
|
||||||
asyncio.gather(*[p.wait() for p in still_running]),
|
|
||||||
timeout=10,
|
|
||||||
),
|
|
||||||
)
|
|
||||||
except TimeoutError:
|
|
||||||
for p in self._procs:
|
|
||||||
if p.returncode is None:
|
|
||||||
with suppress(ProcessLookupError):
|
with suppress(ProcessLookupError):
|
||||||
p.kill()
|
proc.terminate()
|
||||||
await p.wait()
|
try:
|
||||||
|
await asyncio.wait_for(proc.wait(), self._terminate_timeout)
|
||||||
|
except TimeoutError:
|
||||||
|
with suppress(ProcessLookupError):
|
||||||
|
proc.kill()
|
||||||
|
await proc.wait()
|
||||||
|
|
||||||
|
if vital:
|
||||||
|
logger.warning("Vital process %s exited", name)
|
||||||
|
raise CalledProcessError(returncode, cmd)
|
||||||
|
|
||||||
|
started = asyncio.get_running_loop().create_future()
|
||||||
|
self.create_task(run())
|
||||||
|
return await asyncio.shield(started)
|
||||||
|
|
||||||
|
async def wait(self, *waitables: Process | Awaitable) -> tuple[Any, ...]:
|
||||||
|
"""Wait concurrently and return results in argument order."""
|
||||||
|
|
||||||
|
async def task(w: Process | Awaitable) -> Any: # noqa: ANN401
|
||||||
|
if not isinstance(w, Process):
|
||||||
|
return await w
|
||||||
|
if retcode := await w.wait():
|
||||||
|
cmd = self._cmds[w]
|
||||||
|
logger.warning(
|
||||||
|
"Process %s exited with status %d", Path(cmd[0]).stem, retcode
|
||||||
|
)
|
||||||
|
raise CalledProcessError(retcode, cmd)
|
||||||
|
return retcode
|
||||||
|
|
||||||
|
async with asyncio.TaskGroup() as group:
|
||||||
|
tasks = [group.create_task(task(w)) for w in waitables]
|
||||||
|
|
||||||
|
return tuple(task.result() for task in tasks)
|
||||||
|
|
||||||
|
|
||||||
async def http_get_server(url: str, timeout: float) -> str | None: # noqa: ASYNC109
|
async def http_get_server(url: str, timeout: float) -> str | None: # noqa: ASYNC109
|
||||||
@@ -128,42 +107,43 @@ async def http_get_server(url: str, timeout: float) -> str | None: # noqa: ASYN
|
|||||||
writer.close()
|
writer.close()
|
||||||
except OSError, EOFError, ValueError, TimeoutError:
|
except OSError, EOFError, ValueError, TimeoutError:
|
||||||
return None
|
return None
|
||||||
for line in data.decode("latin-1").split("\r\n"):
|
for line in data.decode(errors="replace").split("\r\n"):
|
||||||
if line.lower().startswith("server:"):
|
if line.lower().startswith("server:"):
|
||||||
return line.split(":", 1)[1].strip()
|
return line[7:].strip()
|
||||||
return ""
|
return ""
|
||||||
|
|
||||||
|
|
||||||
async def check_ports_free(*urls: str) -> None:
|
async def check_ports_free(*urls: str) -> None:
|
||||||
"""Verify URLs are not responding (ports are free). Raise SystemExit if any respond."""
|
"""Verify URLs are not responding (ports are free).
|
||||||
|
|
||||||
async def check(url: str) -> None:
|
Meant to run as a task inside a TaskGroup. Logs the conflict and raises
|
||||||
server = await http_get_server(url, timeout=0.1)
|
RuntimeError (handled like a failed process) if any URL responds.
|
||||||
|
"""
|
||||||
|
servers = await asyncio.gather(*(http_get_server(url, timeout=0.1) for url in urls))
|
||||||
|
for url, server in zip(urls, servers, strict=True):
|
||||||
if server is not None:
|
if server is not None:
|
||||||
logger.warning(
|
logger.error(
|
||||||
"Conflicting %s already running at %s", server or "server", url
|
"Conflicting %s already running at %s", server or "server", url
|
||||||
)
|
)
|
||||||
raise SystemExit(1)
|
raise RuntimeError(url)
|
||||||
|
|
||||||
await asyncio.gather(*[check(url) for url in urls])
|
|
||||||
|
|
||||||
|
|
||||||
async def ready(url: str, path: str = "", max_attempts: int = 50) -> None:
|
async def ready(url: str, path: str = "", max_attempts: int = 50) -> None:
|
||||||
"""Wait for the server to be ready by polling an endpoint.
|
"""Wait for the server to be ready by polling an endpoint.
|
||||||
|
|
||||||
Use empty path to disable the check and make this return immediately.
|
Use empty path to disable the check and make this return immediately.
|
||||||
Raises SystemExit(1) if server doesn't start in time.
|
Logs, then raises RuntimeError if the server doesn't start in time.
|
||||||
"""
|
"""
|
||||||
if not path:
|
if not path:
|
||||||
return
|
return
|
||||||
|
|
||||||
for attempt in range(max_attempts):
|
for attempt in range(max_attempts):
|
||||||
if await http_get_server(f"{url}{path}", timeout=1.0) is not None:
|
if await http_get_server(f"{url}{path}", timeout=1.0) is not None:
|
||||||
logger.info("✓ Backend ready!")
|
logger.info("🟢 Backend ready!")
|
||||||
return
|
return
|
||||||
if attempt == max_attempts - 1:
|
if attempt == max_attempts - 1:
|
||||||
logger.warning("Backend didn't start in time")
|
logger.error("Backend at %s didn't start in time", url)
|
||||||
raise SystemExit(1)
|
raise RuntimeError(url)
|
||||||
await asyncio.sleep(0.1)
|
await asyncio.sleep(0.1)
|
||||||
|
|
||||||
|
|
||||||
|
|||||||
Reference in New Issue
Block a user