f85e5149dd
Implement orchestration layer connecting HttpRangeSource to Phase 1.3 xref resolver and Phase 1.4 document model for remote PDF access: - Document::open_remote() public API for remote PDF loading - Progressive tail fetch (16 KB → 1 MB) for startxref location - Xref forward-scan disabled for remote sources (via is_remote check) - Page-by-page on-demand fetch via HttpRangeSource caching - Resource lazy load through XrefResolver cache - HEAD probe with 405 fallback, no Content-Length handling Acceptance criteria: ✅ open_remote(url) returns Document with correct page count ✅ HEAD failure modes (405, no Content-Length, 401) handled ✅ xref forward-scan disabled for remote (is_remote check) ✅ Page-by-page on-demand fetch (HttpRangeSource LRU cache) ✅ INV-8 maintained (all errors return Result) Files modified: - crates/pdftract-core/src/document.rs (Document::open_remote, from_source) - crates/pdftract-core/src/remote.rs (progressive tail fetch) - crates/pdftract-core/src/lib.rs (re-exports) Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
73 lines
2.6 KiB
Python
73 lines
2.6 KiB
Python
#!/usr/bin/env python3
|
|
"""Inspect the content_edit fixtures to debug."""
|
|
|
|
import pikepdf
|
|
import zlib
|
|
|
|
# Check the content of the two PDFs
|
|
with pikepdf.open("tests/fingerprint/fixtures/content_edit_one_glyph/v1.pdf") as pdf1:
|
|
with pikepdf.open("tests/fingerprint/fixtures/content_edit_one_glyph/v2.pdf") as pdf2:
|
|
# Get the content stream
|
|
page1 = pdf1.pages[0]
|
|
page2 = pdf2.pages[0]
|
|
|
|
print("=== v1.pdf ===")
|
|
contents1 = page1.get("/Contents")
|
|
|
|
if isinstance(contents1, pikepdf.Stream):
|
|
data1 = contents1.read_bytes()
|
|
print(f"Stream length: {len(data1)}")
|
|
print(f"Filter: {contents1.get('/Filter')}")
|
|
|
|
# Try decompressing
|
|
try:
|
|
text1 = zlib.decompress(data1, -15).decode("latin-1")
|
|
print(f"Decompressed text: {text1}")
|
|
except Exception as e:
|
|
print(f"Decompress error: {e}")
|
|
print(f"Raw stream (hex): {data1.hex()}")
|
|
|
|
print("\n=== v2.pdf ===")
|
|
contents2 = page2.get("/Contents")
|
|
|
|
if isinstance(contents2, pikepdf.Stream):
|
|
data2 = contents2.read_bytes()
|
|
print(f"Stream length: {len(data2)}")
|
|
print(f"Filter: {contents2.get('/Filter')}")
|
|
|
|
# Try decompressing
|
|
try:
|
|
text2 = zlib.decompress(data2, -15).decode("latin-1")
|
|
print(f"Decompressed text: {text2}")
|
|
except Exception as e:
|
|
print(f"Decompress error: {e}")
|
|
print(f"Raw stream (hex): {data2.hex()}")
|
|
|
|
# Now check the paragraph ones
|
|
print("\n\n=== Paragraph fixtures ===")
|
|
with pikepdf.open("tests/fingerprint/fixtures/content_edit_one_paragraph/v1.pdf") as pdf1:
|
|
with pikepdf.open("tests/fingerprint/fixtures/content_edit_one_paragraph/v2.pdf") as pdf2:
|
|
page1 = pdf1.pages[0]
|
|
page2 = pdf2.pages[0]
|
|
|
|
print("=== v1.pdf ===")
|
|
contents1 = page1.get("/Contents")
|
|
|
|
if isinstance(contents1, pikepdf.Stream):
|
|
data1 = contents1.read_bytes()
|
|
try:
|
|
text1 = zlib.decompress(data1, -15).decode("latin-1")
|
|
print(f"Decompressed text: {text1[:200]}...")
|
|
except Exception as e:
|
|
print(f"Error: {e}")
|
|
|
|
print("\n=== v2.pdf ===")
|
|
contents2 = page2.get("/Contents")
|
|
|
|
if isinstance(contents2, pikepdf.Stream):
|
|
data2 = contents2.read_bytes()
|
|
try:
|
|
text2 = zlib.decompress(data2, -15).decode("latin-1")
|
|
print(f"Decompressed text: {text2[:200]}...")
|
|
except Exception as e:
|
|
print(f"Error: {e}")
|