Teknium
fad88cf130
Same clean-room discipline as the initial rewrite (isolated subagents, functional specs only, predecessor content banned including via git history; transcripts retained). All additions test-proven. docx (13->29 tests): - docx_revisions.py: tracked changes list/accept/reject (all or by id), incl. tables and headers/footers, via direct oxml manipulation - docx_comments.py: list/add/delete comments (native python-docx >=1.2 API with XML fallback), anchored-text extraction - docx_validate.py: package health check (rels, images, styles, CRC) with JSON severity report — explicitly not XSD validation - docx_edit.py: run normalization; TOC + PAGE/NUMPAGES field insertion xlsx (5->12 tests): - xlsx_restructure.py: reference-aware insert/delete rows/cols — rewrites formulas on all sheets (absolute refs, ranges, cross-sheet, quoted names), shifts merges/autofilter/freeze/validation/CF ranges, tables, defined names; JSON report incl. honest not_shifted list - native Excel tables, named ranges, hyperlinks, cell notes, sheet protection (documented as strippable, not security) - xlsx_recalc.py: headless LibreOffice recalc with graceful degrade powerpoint (11->21 tests): - pptx_render.py: all slides -> PNGs (soffice + pdftoppm/pdftocairo), wired to vision_analyze review loop in SKILL.md - run-merge normalize before replace (identical-format splits lossless) - surgical chart ops (series/category/title) wrapping replace_data - slide duplication with rel remap (clean refusal on chart slides) - backgrounds, hyperlinks, slide numbers, footers, notes editing pdf (8->21 tests): - pdf_make_form.py: JSON spec -> AcroForm (text/checkbox/radio/dropdown) - pdf_form_layout.py: pre-build layout lint (bounds/overlap/pairing) + rendered box overlay for vision_analyze review - pdf_page_image.py + shared _raster.py: pypdfium2 -> pdftoppm chain, graceful degrade; connected to scanned-PDF triage flow - pdf_stamp.py: text/image stamps at coordinates (rotation/opacity) - pdf_meta.py: DocInfo metadata + attachments round-trip Gates re-verified independently: 83 skill tests green under LC_ALL=C, repo invariant suite 29/29, SkillEvaluator pii+unicode+lint 3/3 x4.
77 lines
2.6 KiB
Python
77 lines
2.6 KiB
Python
"""Shared page rasterizer with a fallback chain: pypdfium2 -> pdftoppm.
|
|
|
|
Returns PIL Images so callers can annotate/save. Not a CLI.
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import shutil
|
|
import subprocess
|
|
import tempfile
|
|
from pathlib import Path
|
|
|
|
|
|
def available_backends() -> list[str]:
|
|
"""Names of usable rasterizer backends, in preference order."""
|
|
backends = []
|
|
try:
|
|
import pypdfium2 # noqa: F401
|
|
backends.append("pypdfium2")
|
|
except ImportError:
|
|
pass
|
|
if shutil.which("pdftoppm"):
|
|
backends.append("pdftoppm")
|
|
return backends
|
|
|
|
|
|
def missing_hints() -> list[str]:
|
|
"""Install hints for when no backend is available."""
|
|
return [
|
|
"python3 -m pip install pypdfium2",
|
|
"poppler-utils (provides pdftoppm), e.g. apt-get install poppler-utils",
|
|
]
|
|
|
|
|
|
def rasterize_page(pdf_path: str, page: int, dpi: int = 150, password: str | None = None):
|
|
"""Render one 1-based page to a PIL Image, or None if no backend works.
|
|
|
|
Raises ValueError for an out-of-range page when a backend is present.
|
|
"""
|
|
for backend in available_backends():
|
|
if backend == "pypdfium2":
|
|
return _via_pdfium(pdf_path, page, dpi, password)
|
|
if backend == "pdftoppm":
|
|
img = _via_pdftoppm(pdf_path, page, dpi, password)
|
|
if img is not None:
|
|
return img
|
|
return None
|
|
|
|
|
|
def _via_pdfium(pdf_path: str, page: int, dpi: int, password: str | None):
|
|
import pypdfium2 as pdfium
|
|
doc = pdfium.PdfDocument(pdf_path, password=password)
|
|
try:
|
|
if not 1 <= page <= len(doc):
|
|
raise ValueError(f"page {page} out of range 1-{len(doc)}")
|
|
bitmap = doc[page - 1].render(scale=dpi / 72.0)
|
|
return bitmap.to_pil().convert("RGB")
|
|
finally:
|
|
doc.close()
|
|
|
|
|
|
def _via_pdftoppm(pdf_path: str, page: int, dpi: int, password: str | None):
|
|
from PIL import Image
|
|
with tempfile.TemporaryDirectory() as tmp:
|
|
prefix = str(Path(tmp) / "page")
|
|
cmd = ["pdftoppm", "-png", "-r", str(dpi), "-f", str(page), "-l", str(page)]
|
|
if password:
|
|
cmd += ["-upw", password]
|
|
cmd += [pdf_path, prefix]
|
|
proc = subprocess.run(cmd, capture_output=True, text=True, encoding="utf-8")
|
|
if proc.returncode != 0:
|
|
raise ValueError(f"pdftoppm failed: {proc.stderr.strip()}")
|
|
produced = sorted(Path(tmp).glob("page*.png"))
|
|
if not produced:
|
|
raise ValueError(f"page {page} out of range (pdftoppm produced no image)")
|
|
with Image.open(produced[0]) as img:
|
|
return img.convert("RGB")
|