Abimael MartellandClaude Opus 4.6
d9c2143c32
* feat: tagged PDF structure tree support for semantic markdown generation Parse /StructTreeRoot from tagged PDFs and use semantic roles (H1-H6, P, LI, BlockQuote, Code, Caption) to improve markdown output. Structure tree headings add to font-size heuristics without suppressing them. Coverage threshold (≥50%) ensures only properly tagged PDFs activate this path. Phase 1: Parse structure tree with role maps, MCID collection, flattening Phase 2: Capture MCIDs from BMC/BDC operators, tag TextItems Phase 3: Structure-aware markdown generation in convert loop Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: accumulate consecutive code lines into single fenced block Per-line code fencing produced broken markdown for multi-line code blocks (separate ``` open/close per line). Unify struct-tree Code role and font-based monospace detection into a single is_code_line check with in_code_block state for proper accumulation. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * test: add tagged PDF fixture with Firecrawl docs content Synthetic 7-page PDF with rich structure tree exercising H1, H2, H3, P, Code, LI, Caption, TH, TD roles. Generated via fpdf2 script. Integration test verifies struct tree parsing and code fence output. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * chore: remove python PDF generator script from repo Keep the generated fixture PDF but don't track the generator script. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: handle malformed bare-name struct types in tagged PDFs Some PDF generators (e.g. fpdf2) write /S Code instead of /S /Code in structure elements. lopdf silently drops these objects since bare tokens are invalid PDF syntax. Add a pre-processor that scans for known bare struct type names and prepends / before loading. Unifies path and memory loading through the same fix pipeline. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * chore: update lopdf dependency to main branch The firecrawl/zlib-checksum-encrypted branch was merged and deleted. Point to main which includes all previously merged fixes. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * chore: switch lopdf to upstream repo pinned at 845cd3d Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
52 lines
978 B
TOML
52 lines
978 B
TOML
[package]
|
|
name = "pdf-inspector"
|
|
version = "0.1.0"
|
|
edition = "2021"
|
|
autobins = false
|
|
authors = ["Firecrawl Team"]
|
|
description = "Fast PDF inspection, classification, and text extraction with smart scanned vs text-based detection"
|
|
license = "MIT"
|
|
repository = "https://github.com/firecrawl/pdf-inspector"
|
|
|
|
[dependencies]
|
|
# PDF parsing
|
|
lopdf = { git = "https://github.com/J-F-Liu/lopdf", rev = "845cd3d4648d9cefb7b5def5fb387df61ba3a0e5", features = ["rayon"] }
|
|
|
|
# Error handling
|
|
thiserror = "2.0"
|
|
|
|
# Parallel processing
|
|
rayon = "1.10"
|
|
|
|
# Logging
|
|
log = "0.4"
|
|
env_logger = "0.11"
|
|
|
|
# Text processing
|
|
regex = "1.10"
|
|
once_cell = "1.19"
|
|
unicode-normalization = "0.1"
|
|
|
|
# TrueType font parsing (for Identity-H CID font cmap extraction)
|
|
ttf-parser = "0.25"
|
|
|
|
[dev-dependencies]
|
|
tempfile = "3.3"
|
|
|
|
[features]
|
|
default = []
|
|
|
|
[[bin]]
|
|
name = "pdf2md"
|
|
path = "src/bin/pdf2md.rs"
|
|
|
|
[[bin]]
|
|
name = "detect-pdf"
|
|
path = "src/bin/detect_pdf.rs"
|
|
|
|
[[bin]]
|
|
name = "dump_ops"
|
|
path = "src/bin/dump_ops.rs"
|
|
|
|
|