pyr0ball
f941ebdeeb
Extends Pagepiper's document shelving pipeline (renamed from "ingest" — see below) to cover the formats most likely to appear in a real-world engineering document corpus, prompted by scoping a STERIS licensing pitch that needs DOCX/ODT coverage. - Rename the ingest pipeline to "shelve" throughout (scripts/, app/api, tests, docs, frontend). "Glean" (Turnstone's term) was considered and rejected — that's a harvest metaphor for log/knowledge extraction, not a fit for documents entering a library. Documented as a general CF naming principle in the org-level CLAUDE.md. - Wire DOCX into the upload/scan UI, README, and docs — the extraction logic (heading-based chunking, table serialization) already existed but wasn't exposed to users or covered by tests. - Add ODT support via odfpy, mirroring DOCX's chunking strategy. - Add Apple Pages support via headless LibreOffice conversion to ODT. No maintained Python library parses the IWA format directly; libreoffice bundles libetonyek, the only real open-source Pages parser. Adds libreoffice-writer to the Docker image (~300-400MB) for this. - 24 new/updated tests across shelve_docx, shelve_odt, and shelve_pages; full suite (72 tests) passing. Known gaps not addressed here: no Windchill/DocPortal connector exists yet (metadata-only PowerShell recon only), Excel/.xlsx is unsupported, and circuitforge_core.tasks.dispatch_task does not currently exist in circuitforge-core — cf-orch dispatch is dead code, always falling through to local BackgroundTasks. See circuitforge-plans/pagepiper/superpowers/plans/2026-07-10-steris-licensing-pitch.md for the full writeup.
72 lines
2.5 KiB
Python
72 lines
2.5 KiB
Python
# scripts/text_clean.py
|
|
"""
|
|
Shared text-cleaning utilities for shelve pipelines.
|
|
|
|
Removes boilerplate lines injected by ebook converters, piracy watermarks,
|
|
and other non-content artifacts before chunks are stored or embedded.
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import re
|
|
|
|
# Lines that match any of these patterns are dropped entirely.
|
|
# Each pattern is matched against the stripped line (case-insensitive).
|
|
_LINE_DROP_PATTERNS: list[re.Pattern] = [
|
|
# ABC Amber converter family
|
|
re.compile(r'generated by abc amber', re.IGNORECASE),
|
|
re.compile(r'processtext\.com', re.IGNORECASE),
|
|
# Calibre / sigil metadata lines
|
|
re.compile(r'calibre \d+\.\d+', re.IGNORECASE),
|
|
# Standalone URLs (line is just a URL, no surrounding prose)
|
|
re.compile(r'^https?://\S+$'),
|
|
# Common piracy / file-sharing watermarks
|
|
re.compile(r'www\.\w+\.(com|net|org)/\S*book', re.IGNORECASE),
|
|
re.compile(r'downloaded from', re.IGNORECASE),
|
|
re.compile(r'scanned by', re.IGNORECASE),
|
|
re.compile(r'provided by', re.IGNORECASE),
|
|
# Page-number-only lines from PDF extraction (e.g. "- 42 -" or "42")
|
|
re.compile(r'^\s*-?\s*\d{1,4}\s*-?\s*$'),
|
|
]
|
|
|
|
# Inline substrings to strip from within a line before further processing.
|
|
_INLINE_STRIP_PATTERNS: list[re.Pattern] = [
|
|
re.compile(r'generated by abc amber \w+ converter,?\s*https?://\S*', re.IGNORECASE),
|
|
re.compile(r'https?://www\.processtext\.com/\S*', re.IGNORECASE),
|
|
]
|
|
|
|
|
|
def is_artifact_line(line: str) -> bool:
|
|
"""Return True if the line is a known conversion artifact and should be dropped."""
|
|
stripped = line.strip()
|
|
return any(p.search(stripped) for p in _LINE_DROP_PATTERNS)
|
|
|
|
|
|
def clean_line(line: str) -> str:
|
|
"""Strip inline converter artifacts from a line, returning the cleaned version."""
|
|
for p in _INLINE_STRIP_PATTERNS:
|
|
line = p.sub("", line)
|
|
return line.strip()
|
|
|
|
|
|
def clean_paragraph(text: str) -> str:
|
|
"""Clean a multi-line paragraph: drop artifact lines, strip inline artifacts."""
|
|
lines = []
|
|
for line in text.splitlines():
|
|
if is_artifact_line(line):
|
|
continue
|
|
cleaned = clean_line(line)
|
|
if cleaned:
|
|
lines.append(cleaned)
|
|
return "\n".join(lines)
|
|
|
|
|
|
def filter_paragraphs(paragraphs: list[str]) -> list[str]:
|
|
"""Remove artifact lines from a list of paragraph strings."""
|
|
result = []
|
|
for para in paragraphs:
|
|
if is_artifact_line(para):
|
|
continue
|
|
cleaned = clean_line(para)
|
|
if cleaned and len(cleaned.split()) >= 4:
|
|
result.append(cleaned)
|
|
return result
|