diff --git a/pagerite/chunks.py b/pagerite/chunks.py
new file mode 100644
index 0000000..9d118e6
--- /dev/null
+++ b/pagerite/chunks.py
@@ -0,0 +1,150 @@
+"""Block-level Markdown chunking for content-addressed storage.
+
+A page's Markdown is split into deterministic block-level chunks, each
+stored once under its content hash in ``Data.chunks`` (docs/migrate.md).
+Shared by the render/save pipeline (app.py, views.py, i18n.py) and the
+schema migration (migrations.py), so a chunk's key is stable no matter
+where the split happens.
+"""
+
+import re
+
+import blake3
+
+#: Fenced code block opener/closer: up to 3 spaces indent, then 3+
+#: backticks or tildes (CommonMark).
+_FENCE_OPEN = re.compile(r"^ {0,3}(`{3,}|~{3,})")
+
+#: HTML block openers that may span blank lines (CommonMark types 1-5:
+#: script/pre/style/textarea, comments, processing instructions,
+#: declarations, CDATA) with their closing condition. Other HTML blocks
+#: end at the first blank line, which the generic blank-line split
+#: already does.
+_HTML_ATOMIC = (
+    (re.compile(r"^ {0,3}<(?:script|pre|style|textarea)(?:\s|>|$)", re.I),
+     re.compile(r"</(?:script|pre|style|textarea)\s*>", re.I)),
+    (re.compile(r"^ {0,3}<!--"), re.compile(r"-->")),
+    (re.compile(r"^ {0,3}<\?"), re.compile(r"\?>")),
+    (re.compile(r"^ {0,3}<!\[CDATA\["), re.compile(r"\]\]>")),
+    (re.compile(r"^ {0,3}<![A-Za-z]"), re.compile(r">")),
+)
+
+#: First line of a generic HTML block (a block-level tag).
+_HTML_TAG = re.compile(r"^ {0,3}</?[A-Za-z][^>]*>")
+
+
+def _fence_close(line: str, opener: str) -> bool:
+    """True when ``line`` closes a code fence opened by ``opener``: the
+    same marker char, at least as many, and nothing else on the line."""
+    stripped = line.strip()
+    return (
+        len(stripped) >= len(opener)
+        and stripped[0] == opener[0]
+        and set(stripped) == {opener[0]}
+    )
+
+
+def chunk_markdown(markdown: str) -> list[str]:
+    """Split Markdown into block-level chunks, deterministically.
+
+    Blocks are separated by blank lines; fenced code blocks and the
+    multi-line HTML blocks (comments, script/pre/style, CDATA...) are
+    kept atomic, even across blank lines, and end at their closing
+    condition. Chunks carry no surrounding blank lines and no trailing
+    newline; rejoining with ``join_chunks`` reproduces the source modulo
+    blank-line normalization.
+    """
+    chunks: list[str] = []
+    buf: list[str] = []
+    fence = ""  # opener marker of the code fence we are in ("" = outside)
+    html_end: re.Pattern | None = None  # closes the atomic HTML block we are in
+
+    def flush() -> None:
+        text = "\n".join(buf).strip("\n")
+        if text.strip():
+            chunks.append(text)
+        buf.clear()
+
+    for line in markdown.split("\n"):
+        if fence:
+            buf.append(line)
+            if _fence_close(line, fence):
+                fence = ""
+                flush()
+            continue
+        if html_end is not None:
+            buf.append(line)
+            if html_end.search(line):
+                html_end = None
+                flush()
+            continue
+        if not line.strip():
+            flush()
+            continue
+        if m := _FENCE_OPEN.match(line):
+            # Fences interrupt paragraphs (CommonMark): start a new block.
+            flush()
+            fence = m.group(1)
+            buf.append(line)
+            continue
+        if not buf:
+            for open_re, close_re in _HTML_ATOMIC:
+                if open_re.match(line):
+                    buf.append(line)
+                    if close_re.search(line):  # opens and closes on one line
+                        flush()
+                    else:
+                        html_end = close_re
+                    break
+            else:
+                buf.append(line)
+            continue
+        buf.append(line)
+    flush()  # an unterminated fence/HTML block runs to EOF, kept as code/HTML
+    return chunks
+
+
+def _normalize(text: str) -> str:
+    """Whitespace-insensitive chunk identity: strip trailing whitespace
+    per line and collapse surrounding blank lines, so whitespace-only
+    source edits don't invalidate translations."""
+    return "\n".join(line.rstrip() for line in text.split("\n")).strip("\n")
+
+
+def chunk_key(text: str) -> str:
+    """Content key of a chunk: blake3 hex (16-byte digest, 32 hex chars)
+    of the normalized text — the same hasher app.py's file store uses."""
+    return blake3.blake3(_normalize(text).encode()).hexdigest(16)
+
+
+def needs_translation(chunk: str) -> bool:
+    """False for chunks without prose: pure code fences and HTML blocks.
+
+    These are inherently no-translate (docs/migrate.md): derived from the
+    chunk text itself, nothing is stored.
+    """
+    if _FENCE_OPEN.match(chunk):
+        return False
+    first = chunk.split("\n", 1)[0]
+    if any(open_re.match(first) for open_re, _ in _HTML_ATOMIC):
+        return False
+    return not _HTML_TAG.match(first)
+
+
+def join_chunks(chunks: list[str]) -> str:
+    """The stored page form of chunks: blocks joined by a blank line,
+    with a trailing newline ("" for no chunks)."""
+    return "\n\n".join(chunks) + "\n" if chunks else ""
+
+
+def store_chunks(store: dict[str, str], markdown: str) -> list[str]:
+    """Chunk ``markdown`` into ``store`` (hash -> text); return the ordered
+    hashes. Unchanged chunks keep their hashes, so only genuinely new text
+    lands in the kanta change diff. First writer wins: variants sharing a
+    key differ only in insignificant whitespace (see chunk_key)."""
+    hashes = []
+    for chunk in chunk_markdown(markdown):
+        key = chunk_key(chunk)
+        store.setdefault(key, chunk)
+        hashes.append(key)
+    return hashes