marcel/familienarchiv
1
0
Fork 0
Code Issues 107 Pull Requests 1 Actions Packages Projects Releases Wiki Activity

refactor(ocr): extract _observe_block_words for word counter sites

Browse Source 
The two block-iteration loops (/ocr and /ocr/stream's standard generator)
both ran the same word-total and illegible-word increments. Lift them
into a single helper so each call site becomes one line and the counter
intent reads cleanly. Pure refactor — no behavior change, tests stay green.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Marcel
2026-05-21 16:57:18 +02:00
parent 0179e93a4b
commit 22a5ee816a
1 changed files with 14 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
ocr-service/main.py
View File

@@ -50,6 +50,18 @@ ALLOWED_PDF_HOSTS = set(
_SPELL_CHECK_SCRIPT_TYPES = {"HANDWRITING_KURRENT", "HANDWRITING_LATIN"} _SPELL_CHECK_SCRIPT_TYPES = {"HANDWRITING_KURRENT", "HANDWRITING_LATIN"}
def _observe_block_words(words: list[dict], threshold: float) -> None:
"""Record per-block word counts and below-threshold word counts.
Pre: `words` is non-empty. Caller checks for that — keeping the helper
branch-free makes the call sites read as a single line.
"""
metrics.ocr_words_total.inc(len(words))
metrics.ocr_illegible_words_total.inc(
sum(1 for w in words if w["confidence"] < threshold)
)
def _validate_url(url: str) -> None: def _validate_url(url: str) -> None:
"""Validate that the PDF URL points to an allowed host (SSRF protection).""" """Validate that the PDF URL points to an allowed host (SSRF protection)."""
parsed = urlparse(url) parsed = urlparse(url)
@@ -149,10 +161,7 @@ async def run_ocr(request: OcrRequest):
for block in blocks: for block in blocks:
words = block.get("words") or [] words = block.get("words") or []
if words: if words:
metrics.ocr_words_total.inc(len(words)) _observe_block_words(words, threshold)
metrics.ocr_illegible_words_total.inc(
sum(1 for w in words if w["confidence"] < threshold)
)
block["text"] = apply_confidence_markers(words, threshold) block["text"] = apply_confidence_markers(words, threshold)
block.pop("words", None) block.pop("words", None)
if script_type in _SPELL_CHECK_SCRIPT_TYPES: if script_type in _SPELL_CHECK_SCRIPT_TYPES:
@@ -298,10 +307,7 @@ async def run_ocr_stream(request: OcrRequest):
for block in blocks: for block in blocks:
words = block.get("words") or [] words = block.get("words") or []
if words: if words:
metrics.ocr_words_total.inc(len(words)) _observe_block_words(words, threshold)
metrics.ocr_illegible_words_total.inc(
sum(1 for w in words if w["confidence"] < threshold)
)
block["text"] = apply_confidence_markers(words, threshold) block["text"] = apply_confidence_markers(words, threshold)
block.pop("words", None) block.pop("words", None)
if script_type in _SPELL_CHECK_SCRIPT_TYPES: if script_type in _SPELL_CHECK_SCRIPT_TYPES: