pdftract/crates/pdftract-core/Cargo.toml
jedarden d84f8da3a4 feat(pdftract-5qj50): implement mojibake detection and repair via encoding_rs
Implements Phase 4.7 Correction Pipeline step 3: mojibake detection
and repair for Latin-1 bytes misinterpreted as UTF-8.

Changes:
- Add layout::correction module with detect_and_repair_mojibake function
- Implement CorrectableText trait for mutable text access
- Add trait implementations for hybrid::Span and schema::SpanJson
- Make encoding_rs a non-optional dependency (was cjk-gated)
- Detection heuristic: 2+ occurrences of telltale sequences (é, è, ’, etc.)
- Re-decode via encoding_rs::WINDOWS_1252 when detected
- Accept repair only if readability score improves by >0.05 epsilon
- Fast-path pass-through for ASCII-only and clean UTF-8 text

Closes: pdftract-5qj50

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-24 17:01:53 -04:00

82 lines
2.4 KiB
TOML

[package]
name = "pdftract-core"
version.workspace = true
edition.workspace = true
rust-version.workspace = true
license.workspace = true
repository.workspace = true
publish = true
[dependencies]
anyhow = { workspace = true }
hex = "0.4"
image = { version = "0.25", optional = true }
url = { version = "2.5", optional = true }
leptonica-plumbing = { version = "1.4", optional = true }
pdfium-render = { version = "0.9", optional = true }
tesseract = { version = "0.15", optional = true }
indexmap = "2.2"
flate2 = { workspace = true }
lzw = { workspace = true }
memmap2 = "0.9"
regex = "1.10"
secrecy = { workspace = true }
serde = { version = "1.0", features = ["derive"], optional = true }
serde_json = { version = "1.0", optional = true }
schemars = { version = "1.2", features = ["derive"], optional = true }
sha2 = "0.10"
thiserror = { workspace = true }
memchr = { workspace = true }
unicode-normalization = { workspace = true }
ttf-parser = "0.24"
owned_ttf_parser = "0.21"
zstd = "0.13"
rayon = "1.10"
phf = "0.11"
rand = "0.8"
tempfile = "3.10"
tracing = { workspace = true }
dashmap = "6.1"
smallvec = "1.13"
encoding_rs = "0.8"
quick-xml = { version = "0.36", optional = true }
serde_yaml = { version = "0.9", optional = true }
[features]
default = ["serde"]
serde = ["dep:serde", "dep:serde_json", "dep:schemars"]
schemars = ["dep:schemars", "serde"]
receipts = [] # Enable visual citation receipts (SVG clip generation)
ocr = ["dep:image", "dep:leptonica-plumbing", "dep:quick-xml"] # Enable OCR path (image compositing + preprocessing + HOCR parsing)
full-render = ["dep:pdfium-render", "ocr"] # Enable PDFium-based rendering (requires ocr)
remote = ["dep:url"] # Enable remote HTTP source (Phase 1.8)
profiles = ["dep:serde_yaml"] # Enable extraction profiles (Phase 7.10)
proptest = []
fuzzing = [] # Enable cfg(fuzzing) for fuzz harnesses
shape-db = [] # Enable glyph shape database (Level 4 encoding fallback)
cjk = [] # Enable CJK text extraction via predefined CMap registry (~1.2 MB binary size increase)
[dev-dependencies]
chrono = "0.4"
criterion = "0.5"
proptest = "1.4"
quick-xml = "0.36"
regex = "1.10"
serde = { version = "1.0", features = ["derive"] }
serde_json = "1.0"
tempfile = "3.10"
filetime = "0.2"
libc = "0.2"
[[bench]]
name = "table_detection"
harness = false
[[bench]]
name = "wordlist"
harness = false
[build-dependencies]
phf_codegen = "0.11"
serde = { version = "1.0", features = ["derive"] }
serde_json = "1.0"