mu-ref/pdf-inspector
8
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: replace partial_cmp with total_cmp to prevent NaN sort panics (#20)

Browse Source 
* fix sort panics on NaN values from bogus PDF font metrics

Replace all `partial_cmp(...).unwrap_or(Ordering::Equal)` and bare
`partial_cmp(...).unwrap()` with `total_cmp()` across the codebase.

`partial_cmp` returns `None` for NaN, and mapping that to `Equal`
violates total ordering: `a == NaN` and `NaN == b` but `a != b`.
Rust 1.81+ detects this and panics in sort_by. `total_cmp` handles
NaN deterministically (sorts to end) and guarantees total ordering.

The critical crash was in `extract_text_in_regions` (lib.rs:478)
where PDFs with bogus font ascent/descent values produced NaN in
text item coordinates, causing process abort via NAPI.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix missed partial_cmp in layout.rs and restore napi exports

- Convert two remaining b.y.partial_cmp(&a.y) calls to total_cmp
  in group_single_column and column layout sorting
- Restore missing napi exports: detectPdf, extractText,
  extractTextWithPositions, processPdf

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Abimael Martell
2026-04-02 14:39:42 -07:00
committed by GitHub
co-authored by Claude Opus 4.6
parent 732b1b1359
commit fba0a644ef
13 changed files with 137 additions and 137 deletions
Download Patch File Download Diff File Expand all files Collapse all files
napi/index.js
+52 -52
View File
@@ -77,8 +77,8 @@ function requireNative() {
try { try {
const binding = require('firecrawl-pdf-inspector-android-arm64') const binding = require('firecrawl-pdf-inspector-android-arm64')
const bindingPackageVersion = require('firecrawl-pdf-inspector-android-arm64/package.json').version const bindingPackageVersion = require('firecrawl-pdf-inspector-android-arm64/package.json').version
if (bindingPackageVersion !== '0.2.2' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') { if (bindingPackageVersion !== '0.2.3' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
throw new Error(`Native binding package version mismatch, expected 0.2.2 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`) throw new Error(`Native binding package version mismatch, expected 0.2.3 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
} }
return binding return binding
} catch (e) { } catch (e) {
@@ -93,8 +93,8 @@ function requireNative() {
try { try {
const binding = require('firecrawl-pdf-inspector-android-arm-eabi') const binding = require('firecrawl-pdf-inspector-android-arm-eabi')
const bindingPackageVersion = require('firecrawl-pdf-inspector-android-arm-eabi/package.json').version const bindingPackageVersion = require('firecrawl-pdf-inspector-android-arm-eabi/package.json').version
if (bindingPackageVersion !== '0.2.2' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') { if (bindingPackageVersion !== '0.2.3' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
throw new Error(`Native binding package version mismatch, expected 0.2.2 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`) throw new Error(`Native binding package version mismatch, expected 0.2.3 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
} }
return binding return binding
} catch (e) { } catch (e) {
@@ -114,8 +114,8 @@ function requireNative() {
try { try {
const binding = require('firecrawl-pdf-inspector-win32-x64-gnu') const binding = require('firecrawl-pdf-inspector-win32-x64-gnu')
const bindingPackageVersion = require('firecrawl-pdf-inspector-win32-x64-gnu/package.json').version const bindingPackageVersion = require('firecrawl-pdf-inspector-win32-x64-gnu/package.json').version
if (bindingPackageVersion !== '0.2.2' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') { if (bindingPackageVersion !== '0.2.3' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
throw new Error(`Native binding package version mismatch, expected 0.2.2 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`) throw new Error(`Native binding package version mismatch, expected 0.2.3 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
} }
return binding return binding
} catch (e) { } catch (e) {
@@ -130,8 +130,8 @@ function requireNative() {
try { try {
const binding = require('firecrawl-pdf-inspector-win32-x64-msvc') const binding = require('firecrawl-pdf-inspector-win32-x64-msvc')
const bindingPackageVersion = require('firecrawl-pdf-inspector-win32-x64-msvc/package.json').version const bindingPackageVersion = require('firecrawl-pdf-inspector-win32-x64-msvc/package.json').version
if (bindingPackageVersion !== '0.2.2' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') { if (bindingPackageVersion !== '0.2.3' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
throw new Error(`Native binding package version mismatch, expected 0.2.2 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`) throw new Error(`Native binding package version mismatch, expected 0.2.3 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
} }
return binding return binding
} catch (e) { } catch (e) {
@@ -147,8 +147,8 @@ function requireNative() {
try { try {
const binding = require('firecrawl-pdf-inspector-win32-ia32-msvc') const binding = require('firecrawl-pdf-inspector-win32-ia32-msvc')
const bindingPackageVersion = require('firecrawl-pdf-inspector-win32-ia32-msvc/package.json').version const bindingPackageVersion = require('firecrawl-pdf-inspector-win32-ia32-msvc/package.json').version
if (bindingPackageVersion !== '0.2.2' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') { if (bindingPackageVersion !== '0.2.3' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
throw new Error(`Native binding package version mismatch, expected 0.2.2 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`) throw new Error(`Native binding package version mismatch, expected 0.2.3 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
} }
return binding return binding
} catch (e) { } catch (e) {
@@ -163,8 +163,8 @@ function requireNative() {
try { try {
const binding = require('firecrawl-pdf-inspector-win32-arm64-msvc') const binding = require('firecrawl-pdf-inspector-win32-arm64-msvc')
const bindingPackageVersion = require('firecrawl-pdf-inspector-win32-arm64-msvc/package.json').version const bindingPackageVersion = require('firecrawl-pdf-inspector-win32-arm64-msvc/package.json').version
if (bindingPackageVersion !== '0.2.2' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') { if (bindingPackageVersion !== '0.2.3' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
throw new Error(`Native binding package version mismatch, expected 0.2.2 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`) throw new Error(`Native binding package version mismatch, expected 0.2.3 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
} }
return binding return binding
} catch (e) { } catch (e) {
@@ -182,8 +182,8 @@ function requireNative() {
try { try {
const binding = require('firecrawl-pdf-inspector-darwin-universal') const binding = require('firecrawl-pdf-inspector-darwin-universal')
const bindingPackageVersion = require('firecrawl-pdf-inspector-darwin-universal/package.json').version const bindingPackageVersion = require('firecrawl-pdf-inspector-darwin-universal/package.json').version
if (bindingPackageVersion !== '0.2.2' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') { if (bindingPackageVersion !== '0.2.3' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
throw new Error(`Native binding package version mismatch, expected 0.2.2 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`) throw new Error(`Native binding package version mismatch, expected 0.2.3 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
} }
return binding return binding
} catch (e) { } catch (e) {
@@ -198,8 +198,8 @@ function requireNative() {
try { try {
const binding = require('firecrawl-pdf-inspector-darwin-x64') const binding = require('firecrawl-pdf-inspector-darwin-x64')
const bindingPackageVersion = require('firecrawl-pdf-inspector-darwin-x64/package.json').version const bindingPackageVersion = require('firecrawl-pdf-inspector-darwin-x64/package.json').version
if (bindingPackageVersion !== '0.2.2' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') { if (bindingPackageVersion !== '0.2.3' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
throw new Error(`Native binding package version mismatch, expected 0.2.2 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`) throw new Error(`Native binding package version mismatch, expected 0.2.3 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
} }
return binding return binding
} catch (e) { } catch (e) {
@@ -214,8 +214,8 @@ function requireNative() {
try { try {
const binding = require('firecrawl-pdf-inspector-darwin-arm64') const binding = require('firecrawl-pdf-inspector-darwin-arm64')
const bindingPackageVersion = require('firecrawl-pdf-inspector-darwin-arm64/package.json').version const bindingPackageVersion = require('firecrawl-pdf-inspector-darwin-arm64/package.json').version
if (bindingPackageVersion !== '0.2.2' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') { if (bindingPackageVersion !== '0.2.3' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
throw new Error(`Native binding package version mismatch, expected 0.2.2 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`) throw new Error(`Native binding package version mismatch, expected 0.2.3 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
} }
return binding return binding
} catch (e) { } catch (e) {
@@ -234,8 +234,8 @@ function requireNative() {
try { try {
const binding = require('firecrawl-pdf-inspector-freebsd-x64') const binding = require('firecrawl-pdf-inspector-freebsd-x64')
const bindingPackageVersion = require('firecrawl-pdf-inspector-freebsd-x64/package.json').version const bindingPackageVersion = require('firecrawl-pdf-inspector-freebsd-x64/package.json').version
if (bindingPackageVersion !== '0.2.2' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') { if (bindingPackageVersion !== '0.2.3' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
throw new Error(`Native binding package version mismatch, expected 0.2.2 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`) throw new Error(`Native binding package version mismatch, expected 0.2.3 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
} }
return binding return binding
} catch (e) { } catch (e) {
@@ -250,8 +250,8 @@ function requireNative() {
try { try {
const binding = require('firecrawl-pdf-inspector-freebsd-arm64') const binding = require('firecrawl-pdf-inspector-freebsd-arm64')
const bindingPackageVersion = require('firecrawl-pdf-inspector-freebsd-arm64/package.json').version const bindingPackageVersion = require('firecrawl-pdf-inspector-freebsd-arm64/package.json').version
if (bindingPackageVersion !== '0.2.2' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') { if (bindingPackageVersion !== '0.2.3' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
throw new Error(`Native binding package version mismatch, expected 0.2.2 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`) throw new Error(`Native binding package version mismatch, expected 0.2.3 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
} }
return binding return binding
} catch (e) { } catch (e) {
@@ -271,8 +271,8 @@ function requireNative() {
try { try {
const binding = require('firecrawl-pdf-inspector-linux-x64-musl') const binding = require('firecrawl-pdf-inspector-linux-x64-musl')
const bindingPackageVersion = require('firecrawl-pdf-inspector-linux-x64-musl/package.json').version const bindingPackageVersion = require('firecrawl-pdf-inspector-linux-x64-musl/package.json').version
if (bindingPackageVersion !== '0.2.2' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') { if (bindingPackageVersion !== '0.2.3' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
throw new Error(`Native binding package version mismatch, expected 0.2.2 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`) throw new Error(`Native binding package version mismatch, expected 0.2.3 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
} }
return binding return binding
} catch (e) { } catch (e) {
@@ -287,8 +287,8 @@ function requireNative() {
try { try {
const binding = require('firecrawl-pdf-inspector-linux-x64-gnu') const binding = require('firecrawl-pdf-inspector-linux-x64-gnu')
const bindingPackageVersion = require('firecrawl-pdf-inspector-linux-x64-gnu/package.json').version const bindingPackageVersion = require('firecrawl-pdf-inspector-linux-x64-gnu/package.json').version
if (bindingPackageVersion !== '0.2.2' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') { if (bindingPackageVersion !== '0.2.3' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
throw new Error(`Native binding package version mismatch, expected 0.2.2 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`) throw new Error(`Native binding package version mismatch, expected 0.2.3 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
} }
return binding return binding
} catch (e) { } catch (e) {
@@ -305,8 +305,8 @@ function requireNative() {
try { try {
const binding = require('firecrawl-pdf-inspector-linux-arm64-musl') const binding = require('firecrawl-pdf-inspector-linux-arm64-musl')
const bindingPackageVersion = require('firecrawl-pdf-inspector-linux-arm64-musl/package.json').version const bindingPackageVersion = require('firecrawl-pdf-inspector-linux-arm64-musl/package.json').version
if (bindingPackageVersion !== '0.2.2' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') { if (bindingPackageVersion !== '0.2.3' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
throw new Error(`Native binding package version mismatch, expected 0.2.2 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`) throw new Error(`Native binding package version mismatch, expected 0.2.3 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
} }
return binding return binding
} catch (e) { } catch (e) {
@@ -321,8 +321,8 @@ function requireNative() {
try { try {
const binding = require('firecrawl-pdf-inspector-linux-arm64-gnu') const binding = require('firecrawl-pdf-inspector-linux-arm64-gnu')
const bindingPackageVersion = require('firecrawl-pdf-inspector-linux-arm64-gnu/package.json').version const bindingPackageVersion = require('firecrawl-pdf-inspector-linux-arm64-gnu/package.json').version
if (bindingPackageVersion !== '0.2.2' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') { if (bindingPackageVersion !== '0.2.3' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
throw new Error(`Native binding package version mismatch, expected 0.2.2 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`) throw new Error(`Native binding package version mismatch, expected 0.2.3 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
} }
return binding return binding
} catch (e) { } catch (e) {
@@ -339,8 +339,8 @@ function requireNative() {
try { try {
const binding = require('firecrawl-pdf-inspector-linux-arm-musleabihf') const binding = require('firecrawl-pdf-inspector-linux-arm-musleabihf')
const bindingPackageVersion = require('firecrawl-pdf-inspector-linux-arm-musleabihf/package.json').version const bindingPackageVersion = require('firecrawl-pdf-inspector-linux-arm-musleabihf/package.json').version
if (bindingPackageVersion !== '0.2.2' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') { if (bindingPackageVersion !== '0.2.3' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
throw new Error(`Native binding package version mismatch, expected 0.2.2 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`) throw new Error(`Native binding package version mismatch, expected 0.2.3 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
} }
return binding return binding
} catch (e) { } catch (e) {
@@ -355,8 +355,8 @@ function requireNative() {
try { try {
const binding = require('firecrawl-pdf-inspector-linux-arm-gnueabihf') const binding = require('firecrawl-pdf-inspector-linux-arm-gnueabihf')
const bindingPackageVersion = require('firecrawl-pdf-inspector-linux-arm-gnueabihf/package.json').version const bindingPackageVersion = require('firecrawl-pdf-inspector-linux-arm-gnueabihf/package.json').version
if (bindingPackageVersion !== '0.2.2' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') { if (bindingPackageVersion !== '0.2.3' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
throw new Error(`Native binding package version mismatch, expected 0.2.2 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`) throw new Error(`Native binding package version mismatch, expected 0.2.3 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
} }
return binding return binding
} catch (e) { } catch (e) {
@@ -373,8 +373,8 @@ function requireNative() {
try { try {
const binding = require('firecrawl-pdf-inspector-linux-loong64-musl') const binding = require('firecrawl-pdf-inspector-linux-loong64-musl')
const bindingPackageVersion = require('firecrawl-pdf-inspector-linux-loong64-musl/package.json').version const bindingPackageVersion = require('firecrawl-pdf-inspector-linux-loong64-musl/package.json').version
if (bindingPackageVersion !== '0.2.2' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') { if (bindingPackageVersion !== '0.2.3' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
throw new Error(`Native binding package version mismatch, expected 0.2.2 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`) throw new Error(`Native binding package version mismatch, expected 0.2.3 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
} }
return binding return binding
} catch (e) { } catch (e) {
@@ -389,8 +389,8 @@ function requireNative() {
try { try {
const binding = require('firecrawl-pdf-inspector-linux-loong64-gnu') const binding = require('firecrawl-pdf-inspector-linux-loong64-gnu')
const bindingPackageVersion = require('firecrawl-pdf-inspector-linux-loong64-gnu/package.json').version const bindingPackageVersion = require('firecrawl-pdf-inspector-linux-loong64-gnu/package.json').version
if (bindingPackageVersion !== '0.2.2' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') { if (bindingPackageVersion !== '0.2.3' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
throw new Error(`Native binding package version mismatch, expected 0.2.2 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`) throw new Error(`Native binding package version mismatch, expected 0.2.3 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
} }
return binding return binding
} catch (e) { } catch (e) {
@@ -407,8 +407,8 @@ function requireNative() {
try { try {
const binding = require('firecrawl-pdf-inspector-linux-riscv64-musl') const binding = require('firecrawl-pdf-inspector-linux-riscv64-musl')
const bindingPackageVersion = require('firecrawl-pdf-inspector-linux-riscv64-musl/package.json').version const bindingPackageVersion = require('firecrawl-pdf-inspector-linux-riscv64-musl/package.json').version
if (bindingPackageVersion !== '0.2.2' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') { if (bindingPackageVersion !== '0.2.3' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
throw new Error(`Native binding package version mismatch, expected 0.2.2 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`) throw new Error(`Native binding package version mismatch, expected 0.2.3 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
} }
return binding return binding
} catch (e) { } catch (e) {
@@ -423,8 +423,8 @@ function requireNative() {
try { try {
const binding = require('firecrawl-pdf-inspector-linux-riscv64-gnu') const binding = require('firecrawl-pdf-inspector-linux-riscv64-gnu')
const bindingPackageVersion = require('firecrawl-pdf-inspector-linux-riscv64-gnu/package.json').version const bindingPackageVersion = require('firecrawl-pdf-inspector-linux-riscv64-gnu/package.json').version
if (bindingPackageVersion !== '0.2.2' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') { if (bindingPackageVersion !== '0.2.3' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
throw new Error(`Native binding package version mismatch, expected 0.2.2 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`) throw new Error(`Native binding package version mismatch, expected 0.2.3 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
} }
return binding return binding
} catch (e) { } catch (e) {
@@ -440,8 +440,8 @@ function requireNative() {
try { try {
const binding = require('firecrawl-pdf-inspector-linux-ppc64-gnu') const binding = require('firecrawl-pdf-inspector-linux-ppc64-gnu')
const bindingPackageVersion = require('firecrawl-pdf-inspector-linux-ppc64-gnu/package.json').version const bindingPackageVersion = require('firecrawl-pdf-inspector-linux-ppc64-gnu/package.json').version
if (bindingPackageVersion !== '0.2.2' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') { if (bindingPackageVersion !== '0.2.3' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
throw new Error(`Native binding package version mismatch, expected 0.2.2 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`) throw new Error(`Native binding package version mismatch, expected 0.2.3 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
} }
return binding return binding
} catch (e) { } catch (e) {
@@ -456,8 +456,8 @@ function requireNative() {
try { try {
const binding = require('firecrawl-pdf-inspector-linux-s390x-gnu') const binding = require('firecrawl-pdf-inspector-linux-s390x-gnu')
const bindingPackageVersion = require('firecrawl-pdf-inspector-linux-s390x-gnu/package.json').version const bindingPackageVersion = require('firecrawl-pdf-inspector-linux-s390x-gnu/package.json').version
if (bindingPackageVersion !== '0.2.2' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') { if (bindingPackageVersion !== '0.2.3' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
throw new Error(`Native binding package version mismatch, expected 0.2.2 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`) throw new Error(`Native binding package version mismatch, expected 0.2.3 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
} }
return binding return binding
} catch (e) { } catch (e) {
@@ -476,8 +476,8 @@ function requireNative() {
try { try {
const binding = require('firecrawl-pdf-inspector-openharmony-arm64') const binding = require('firecrawl-pdf-inspector-openharmony-arm64')
const bindingPackageVersion = require('firecrawl-pdf-inspector-openharmony-arm64/package.json').version const bindingPackageVersion = require('firecrawl-pdf-inspector-openharmony-arm64/package.json').version
if (bindingPackageVersion !== '0.2.2' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') { if (bindingPackageVersion !== '0.2.3' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
throw new Error(`Native binding package version mismatch, expected 0.2.2 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`) throw new Error(`Native binding package version mismatch, expected 0.2.3 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
} }
return binding return binding
} catch (e) { } catch (e) {
@@ -492,8 +492,8 @@ function requireNative() {
try { try {
const binding = require('firecrawl-pdf-inspector-openharmony-x64') const binding = require('firecrawl-pdf-inspector-openharmony-x64')
const bindingPackageVersion = require('firecrawl-pdf-inspector-openharmony-x64/package.json').version const bindingPackageVersion = require('firecrawl-pdf-inspector-openharmony-x64/package.json').version
if (bindingPackageVersion !== '0.2.2' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') { if (bindingPackageVersion !== '0.2.3' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
throw new Error(`Native binding package version mismatch, expected 0.2.2 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`) throw new Error(`Native binding package version mismatch, expected 0.2.3 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
} }
return binding return binding
} catch (e) { } catch (e) {
@@ -508,8 +508,8 @@ function requireNative() {
try { try {
const binding = require('firecrawl-pdf-inspector-openharmony-arm') const binding = require('firecrawl-pdf-inspector-openharmony-arm')
const bindingPackageVersion = require('firecrawl-pdf-inspector-openharmony-arm/package.json').version const bindingPackageVersion = require('firecrawl-pdf-inspector-openharmony-arm/package.json').version
if (bindingPackageVersion !== '0.2.2' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') { if (bindingPackageVersion !== '0.2.3' && process.env.NAPI_RS_ENFORCE_VERSION_CHECK && process.env.NAPI_RS_ENFORCE_VERSION_CHECK !== '0') {
throw new Error(`Native binding package version mismatch, expected 0.2.2 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`) throw new Error(`Native binding package version mismatch, expected 0.2.3 but got ${bindingPackageVersion}. You can reinstall dependencies to fix this issue.`)
} }
return binding return binding
} catch (e) { } catch (e) {
src/extractor/layout.rs
+9 -17
View File
@@ -218,7 +218,7 @@ fn columns_have_prose(columns: &[ColumnRegion], items: &[&TextItem]) -> bool {
// Sort by Y descending (top of page = higher Y in PDF coords) // Sort by Y descending (top of page = higher Y in PDF coords)
let mut sorted: Vec<&TextItem> = col_items; let mut sorted: Vec<&TextItem> = col_items;
sorted.sort_by(|a, b| b.y.partial_cmp(&a.y).unwrap_or(std::cmp::Ordering::Equal)); sorted.sort_by(|a, b| b.y.total_cmp(&a.y));
// Group into lines by Y-proximity and measure fill + item count // Group into lines by Y-proximity and measure fill + item count
let mut full_lines = 0usize; let mut full_lines = 0usize;
@@ -616,7 +616,7 @@ fn identify_spanning_lines(items: &[TextItem], columns: &[ColumnRegion]) -> Vec<
// Build (original_index, y) pairs sorted by Y descending for grouping // Build (original_index, y) pairs sorted by Y descending for grouping
let mut indexed: Vec<(usize, f32)> = let mut indexed: Vec<(usize, f32)> =
items.iter().enumerate().map(|(i, it)| (i, it.y)).collect(); items.iter().enumerate().map(|(i, it)| (i, it.y)).collect();
indexed.sort_by(|a, b| b.1.partial_cmp(&a.1).unwrap_or(std::cmp::Ordering::Equal)); indexed.sort_by(|a, b| b.1.total_cmp(&a.1));
// Group by Y-proximity into rough lines (as index sets) // Group by Y-proximity into rough lines (as index sets)
let mut groups: Vec<Vec<usize>> = Vec::new(); let mut groups: Vec<Vec<usize>> = Vec::new();
@@ -778,7 +778,7 @@ pub(crate) fn is_newspaper_layout(
return 0.0; return 0.0;
} }
let mut ys: Vec<f32> = lines.iter().map(|l| l.y).collect(); let mut ys: Vec<f32> = lines.iter().map(|l| l.y).collect();
ys.sort_by(|a, b| a.partial_cmp(b).unwrap()); ys.sort_by(|a, b| a.total_cmp(b));
let span = ys.last().unwrap() - ys.first().unwrap(); let span = ys.last().unwrap() - ys.first().unwrap();
span / (lines.len() as f32 - 1.0) span / (lines.len() as f32 - 1.0)
}; };
@@ -845,7 +845,7 @@ fn split_column_stragglers(lines: Vec<TextLine>) -> (Vec<TextLine>, Vec<TextLine
// Median gap = typical line spacing // Median gap = typical line spacing
let mut sorted_gaps = gaps.clone(); let mut sorted_gaps = gaps.clone();
sorted_gaps.sort_by(|a, b| a.partial_cmp(b).unwrap_or(std::cmp::Ordering::Equal)); sorted_gaps.sort_by(|a, b| a.total_cmp(b));
let median_gap = sorted_gaps[sorted_gaps.len() / 2]; let median_gap = sorted_gaps[sorted_gaps.len() / 2];
// A gap > 3× median (min 30pt) indicates a break between content clusters // A gap > 3× median (min 30pt) indicates a break between content clusters
@@ -1078,9 +1078,8 @@ pub(crate) fn group_into_lines_with_thresholds(
} }
} }
above.sort_by(|a, b| b.y.partial_cmp(&a.y).unwrap_or(std::cmp::Ordering::Equal)); above.sort_by(|a, b| b.y.total_cmp(&a.y));
below_spanning below_spanning.sort_by(|a, b| b.y.total_cmp(&a.y));
.sort_by(|a, b| b.y.partial_cmp(&a.y).unwrap_or(std::cmp::Ordering::Equal));
all_lines.extend(above); all_lines.extend(above);
for col in core_columns { for col in core_columns {
@@ -1101,15 +1100,12 @@ pub(crate) fn group_into_lines_with_thresholds(
// Sort by Y descending (top-first), then by X for same-Y lines // Sort by Y descending (top-first), then by X for same-Y lines
all_page_lines.sort_by(|a, b| { all_page_lines.sort_by(|a, b| {
b.y.partial_cmp(&a.y) b.y.total_cmp(&a.y).then(
.unwrap_or(std::cmp::Ordering::Equal)
.then(
a.items a.items
.first() .first()
.map(|i| i.x) .map(|i| i.x)
.unwrap_or(0.0) .unwrap_or(0.0)
.partial_cmp(&b.items.first().map(|i| i.x).unwrap_or(0.0)) .total_cmp(&b.items.first().map(|i| i.x).unwrap_or(0.0)),
.unwrap_or(std::cmp::Ordering::Equal),
) )
}); });
@@ -1185,11 +1181,7 @@ fn group_single_column(items: Vec<TextItem>, adaptive_threshold: f32) -> Vec<Tex
let items = if use_y_sorting { let items = if use_y_sorting {
// Sort by Y descending (top to bottom in PDF coords) // Sort by Y descending (top to bottom in PDF coords)
let mut sorted = items; let mut sorted = items;
sorted.sort_by(|a, b| { sorted.sort_by(|a, b| b.y.total_cmp(&a.y).then(a.x.total_cmp(&b.x)));
b.y.partial_cmp(&a.y)
.unwrap_or(std::cmp::Ordering::Equal)
.then(a.x.partial_cmp(&b.x).unwrap_or(std::cmp::Ordering::Equal))
});
sorted sorted
} else { } else {
items items
src/extractor/mod.rs
+4 -7
View File
@@ -334,17 +334,14 @@ pub(crate) fn merge_text_items(items: Vec<TextItem>) -> Vec<TextItem> {
for (_, _, group) in &mut line_groups { for (_, _, group) in &mut line_groups {
let rtl = is_rtl_text(group.iter().map(|i| &i.text)); let rtl = is_rtl_text(group.iter().map(|i| &i.text));
if rtl { if rtl {
group.sort_by(|a, b| b.x.partial_cmp(&a.x).unwrap_or(std::cmp::Ordering::Equal)); group.sort_by(|a, b| b.x.total_cmp(&a.x));
} else { } else {
group.sort_by(|a, b| a.x.partial_cmp(&b.x).unwrap_or(std::cmp::Ordering::Equal)); group.sort_by(|a, b| a.x.total_cmp(&b.x));
} }
} }
// Sort groups by page then Y descending (top of page first) // Sort groups by page then Y descending (top of page first)
line_groups.sort_by(|a, b| { line_groups.sort_by(|a, b| a.0.cmp(&b.0).then_with(|| b.1.total_cmp(&a.1)));
a.0.cmp(&b.0)
.then_with(|| b.1.partial_cmp(&a.1).unwrap_or(std::cmp::Ordering::Equal))
});
let mut merged = Vec::new(); let mut merged = Vec::new();
@@ -452,7 +449,7 @@ pub(crate) fn merge_subscript_items(items: Vec<TextItem>) -> Vec<TextItem> {
for (_, _, mut group) in line_groups { for (_, _, mut group) in line_groups {
// Sort by X position // Sort by X position
group.sort_by(|a, b| a.x.partial_cmp(&b.x).unwrap_or(std::cmp::Ordering::Equal)); group.sort_by(|a, b| a.x.total_cmp(&b.x));
// Find the dominant (most common) font size in this group // Find the dominant (most common) font size in this group
let max_fs = group.iter().map(|i| i.font_size).fold(0.0_f32, f32::max); let max_fs = group.iter().map(|i| i.font_size).fold(0.0_f32, f32::max);
src/lib.rs
+21 -8
View File
@@ -477,16 +477,29 @@ fn collect_text_in_region(
return String::new(); return String::new();
} }
// Sort top→bottom (descending Y in bottom-left coords), then left→right // Sort top→bottom (descending Y in bottom-left coords), then left→right.
// Uses total_cmp to avoid panics on NaN values from bogus font metrics.
matched.sort_by(|a, b| { matched.sort_by(|a, b| {
let line_threshold = a.font_size.max(b.font_size) * 0.5; let fs_a = if a.font_size.is_finite() {
let y_diff = b.y - a.y; // descending Y = top to bottom a.font_size
if y_diff.abs() < line_threshold {
a.x.partial_cmp(&b.x).unwrap_or(std::cmp::Ordering::Equal)
} else { } else {
y_diff 0.0
.partial_cmp(&0.0_f32) };
.unwrap_or(std::cmp::Ordering::Equal) let fs_b = if b.font_size.is_finite() {
b.font_size
} else {
0.0
};
let line_threshold = fs_a.max(fs_b) * 0.5;
let ay = if a.y.is_finite() { a.y } else { 0.0 };
let by = if b.y.is_finite() { b.y } else { 0.0 };
let y_diff = by - ay; // descending Y = top to bottom
if y_diff.abs() < line_threshold {
let ax = if a.x.is_finite() { a.x } else { 0.0 };
let bx = if b.x.is_finite() { b.x } else { 0.0 };
ax.total_cmp(&bx)
} else {
by.total_cmp(&ay)
} }
}); });
src/markdown/analysis.rs
+2 -2
View File
@@ -121,7 +121,7 @@ pub(crate) fn compute_paragraph_threshold(lines: &[TextLine], base_size: f32) ->
return fallback; return fallback;
} }
gaps.sort_by(|a, b| a.partial_cmp(b).unwrap_or(std::cmp::Ordering::Equal)); gaps.sort_by(|a, b| a.total_cmp(b));
let median = gaps[gaps.len() / 2]; let median = gaps[gaps.len() / 2];
@@ -221,7 +221,7 @@ pub(crate) fn compute_heading_tiers(lines: &[TextLine], base_size: f32) -> Vec<f
} }
// Sort descending // Sort descending
heading_sizes.sort_by(|a, b| b.partial_cmp(a).unwrap_or(std::cmp::Ordering::Equal)); heading_sizes.sort_by(|a, b| b.total_cmp(a));
// Cluster sizes within 0.5pt into same tier (use first value as representative) // Cluster sizes within 0.5pt into same tier (use first value as representative)
let mut tiers: Vec<f32> = Vec::new(); let mut tiers: Vec<f32> = Vec::new();
src/markdown/mod.rs
+4 -4
View File
@@ -42,7 +42,7 @@ pub(crate) fn split_side_by_side(items: &[TextItem]) -> Vec<(f32, f32)> {
// Sort items by left edge // Sort items by left edge
let mut xs: Vec<f32> = items.iter().map(|i| i.x).collect(); let mut xs: Vec<f32> = items.iter().map(|i| i.x).collect();
xs.sort_by(|a, b| a.partial_cmp(b).unwrap_or(std::cmp::Ordering::Equal)); xs.sort_by(|a, b| a.total_cmp(b));
// Find all candidate gaps: ≥30pt, in the middle 60% of the X range, // Find all candidate gaps: ≥30pt, in the middle 60% of the X range,
// with ≥20 items on each side. // with ≥20 items on each side.
@@ -118,7 +118,7 @@ pub(crate) fn split_side_by_side(items: &[TextItem]) -> Vec<(f32, f32)> {
}) })
.copied() .copied()
.collect(); .collect();
balanced_positions.sort_by(|a, b| a.partial_cmp(b).unwrap_or(std::cmp::Ordering::Equal)); balanced_positions.sort_by(|a, b| a.total_cmp(b));
balanced_positions.dedup_by(|a, b| (*a - *b).abs() < 50.0); balanced_positions.dedup_by(|a, b| (*a - *b).abs() < 50.0);
if balanced_positions.len() > 1 { if balanced_positions.len() > 1 {
return vec![]; return vec![];
@@ -209,7 +209,7 @@ fn split_from_hint_regions(items: &[TextItem], rects: &[PdfRect], page: u32) ->
// Width outlier filter (same as detect_tables_from_rects) // Width outlier filter (same as detect_tables_from_rects)
let mut widths: Vec<f32> = page_rects.iter().map(|&(_, _, w, _)| w).collect(); let mut widths: Vec<f32> = page_rects.iter().map(|&(_, _, w, _)| w).collect();
widths.sort_by(|a, b| a.partial_cmp(b).unwrap_or(std::cmp::Ordering::Equal)); widths.sort_by(|a, b| a.total_cmp(b));
let median_width = widths[widths.len() / 2]; let median_width = widths[widths.len() / 2];
page_rects.retain(|&(_, _, w, _)| w <= median_width * 10.0); page_rects.retain(|&(_, _, w, _)| w <= median_width * 10.0);
@@ -1037,7 +1037,7 @@ pub(crate) fn to_markdown_from_items_with_rects_and_lines(
} }
// Sort by Y descending (top to bottom) so left and right // Sort by Y descending (top to bottom) so left and right
// band lines interleave in visual reading order. // band lines interleave in visual reading order.
page_lines.sort_by(|a, b| b.y.partial_cmp(&a.y).unwrap_or(std::cmp::Ordering::Equal)); page_lines.sort_by(|a, b| b.y.total_cmp(&a.y));
all_lines.extend(page_lines); all_lines.extend(page_lines);
} }
all_lines all_lines
src/markdown/preprocess.rs
+1 -1
View File
@@ -275,7 +275,7 @@ pub(crate) fn strip_repeated_lines(lines: Vec<TextLine>, page_count: u32) -> Vec
page_sorted_ys.entry(line.page).or_default().push(line.y); page_sorted_ys.entry(line.page).or_default().push(line.y);
} }
for ys in page_sorted_ys.values_mut() { for ys in page_sorted_ys.values_mut() {
ys.sort_by(|a, b| a.partial_cmp(b).unwrap_or(std::cmp::Ordering::Equal)); ys.sort_by(|a, b| a.total_cmp(b));
ys.dedup(); ys.dedup();
} }
src/tables/detect_heuristic.rs
+7 -9
View File
@@ -48,7 +48,7 @@ pub(crate) fn merge_adjacent_items(items: &[TextItem]) -> (Vec<TextItem>, Vec<Ve
} }
// Sort groups by Y descending (top of page first) // Sort groups by Y descending (top of page first)
line_groups.sort_by(|a, b| b.0.partial_cmp(&a.0).unwrap_or(std::cmp::Ordering::Equal)); line_groups.sort_by(|a, b| b.0.total_cmp(&a.0));
let mut merged_items = Vec::new(); let mut merged_items = Vec::new();
let mut index_map: Vec<Vec<usize>> = Vec::new(); let mut index_map: Vec<Vec<usize>> = Vec::new();
@@ -284,7 +284,7 @@ fn find_table_regions(items: &[(usize, &TextItem)]) -> Vec<(f32, f32)> {
} }
let mut y_positions: Vec<f32> = items.iter().map(|(_, i)| i.y).collect(); let mut y_positions: Vec<f32> = items.iter().map(|(_, i)| i.y).collect();
y_positions.sort_by(|a, b| a.partial_cmp(b).unwrap_or(std::cmp::Ordering::Equal)); y_positions.sort_by(|a, b| a.total_cmp(b));
// Find clusters of Y positions (table regions) // Find clusters of Y positions (table regions)
let mut regions = Vec::new(); let mut regions = Vec::new();
@@ -347,7 +347,7 @@ fn find_table_regions_strict(items: &[(usize, &TextItem)]) -> Vec<(f32, f32, f32
let mut qualifying_rows: Vec<(f32, Vec<f32>)> = Vec::new(); // (y, cluster_starts) let mut qualifying_rows: Vec<(f32, Vec<f32>)> = Vec::new(); // (y, cluster_starts)
for (y, x_positions) in &row_groups { for (y, x_positions) in &row_groups {
let mut sorted_xs = x_positions.clone(); let mut sorted_xs = x_positions.clone();
sorted_xs.sort_by(|a, b| a.partial_cmp(b).unwrap_or(std::cmp::Ordering::Equal)); sorted_xs.sort_by(|a, b| a.total_cmp(b));
if sorted_xs.is_empty() { if sorted_xs.is_empty() {
continue; continue;
@@ -379,14 +379,14 @@ fn find_table_regions_strict(items: &[(usize, &TextItem)]) -> Vec<(f32, f32, f32
// Step 3: Find contiguous runs of qualifying rows. // Step 3: Find contiguous runs of qualifying rows.
// Use adaptive gap: median spacing × 3 (handles wrapped cells where // Use adaptive gap: median spacing × 3 (handles wrapped cells where
// qualifying rows are spaced further apart), with a floor of 25pt. // qualifying rows are spaced further apart), with a floor of 25pt.
qualifying_rows.sort_by(|a, b| a.0.partial_cmp(&b.0).unwrap_or(std::cmp::Ordering::Equal)); qualifying_rows.sort_by(|a, b| a.0.total_cmp(&b.0));
let max_gap = if qualifying_rows.len() >= 3 { let max_gap = if qualifying_rows.len() >= 3 {
let mut gaps: Vec<f32> = qualifying_rows let mut gaps: Vec<f32> = qualifying_rows
.windows(2) .windows(2)
.map(|w| (w[1].0 - w[0].0).abs()) .map(|w| (w[1].0 - w[0].0).abs())
.collect(); .collect();
gaps.sort_by(|a, b| a.partial_cmp(b).unwrap_or(std::cmp::Ordering::Equal)); gaps.sort_by(|a, b| a.total_cmp(b));
let median_gap = gaps[gaps.len() / 2]; let median_gap = gaps[gaps.len() / 2];
(median_gap * 3.0).max(25.0) (median_gap * 3.0).max(25.0)
} else { } else {
@@ -566,11 +566,9 @@ fn detect_table_in_region(items: &[(usize, &TextItem)], mode: TableDetectionMode
// Sort by X position (direction-aware) // Sort by X position (direction-aware)
let rtl = is_rtl_text(col_items.iter().map(|i| &i.text)); let rtl = is_rtl_text(col_items.iter().map(|i| &i.text));
if rtl { if rtl {
col_items col_items.sort_by(|a, b| b.x.total_cmp(&a.x));
.sort_by(|a, b| b.x.partial_cmp(&a.x).unwrap_or(std::cmp::Ordering::Equal));
} else { } else {
col_items col_items.sort_by(|a, b| a.x.total_cmp(&b.x));
.sort_by(|a, b| a.x.partial_cmp(&b.x).unwrap_or(std::cmp::Ordering::Equal));
} }
// Join items with subscript-aware spacing // Join items with subscript-aware spacing
src/tables/detect_lines.rs
+1 -1
View File
@@ -167,7 +167,7 @@ pub fn detect_tables_from_lines(items: &[TextItem], lines: &[PdfLine], page: u32
// Row edges need to be in descending order (top of page = higher Y first) // Row edges need to be in descending order (top of page = higher Y first)
let mut row_edges_desc = row_edges; let mut row_edges_desc = row_edges;
row_edges_desc.sort_by(|a, b| b.partial_cmp(a).unwrap_or(std::cmp::Ordering::Equal)); row_edges_desc.sort_by(|a, b| b.total_cmp(a));
log::debug!( log::debug!(
"detect_lines p{}: {} row_edges, {} col_edges, table=({:.0},{:.0})-({:.0},{:.0}), spanning_h={}, spanning_v={}", "detect_lines p{}: {} row_edges, {} col_edges, table=({:.0},{:.0})-({:.0},{:.0}), spanning_h={}, spanning_v={}",
src/tables/detect_rects.rs
+17 -17
View File
@@ -144,7 +144,7 @@ fn split_wide_cluster(
// Build sorted list of X-intervals (x_left, x_right) from each rect // Build sorted list of X-intervals (x_left, x_right) from each rect
let mut intervals: Vec<(f32, f32)> = rects.iter().map(|&(x, _, w, _)| (x, x + w)).collect(); let mut intervals: Vec<(f32, f32)> = rects.iter().map(|&(x, _, w, _)| (x, x + w)).collect();
intervals.sort_by(|a, b| a.0.partial_cmp(&b.0).unwrap_or(std::cmp::Ordering::Equal)); intervals.sort_by(|a, b| a.0.total_cmp(&b.0));
// Merge overlapping intervals to find contiguous X-bands // Merge overlapping intervals to find contiguous X-bands
let mut merged: Vec<(f32, f32)> = Vec::new(); let mut merged: Vec<(f32, f32)> = Vec::new();
@@ -262,7 +262,7 @@ pub fn detect_tables_from_rects(
// background fills stand out clearly. // background fills stand out clearly.
if page_rects.len() >= 6 { if page_rects.len() >= 6 {
let mut widths: Vec<f32> = page_rects.iter().map(|&(_, _, w, _)| w).collect(); let mut widths: Vec<f32> = page_rects.iter().map(|&(_, _, w, _)| w).collect();
widths.sort_by(|a, b| a.partial_cmp(b).unwrap_or(std::cmp::Ordering::Equal)); widths.sort_by(|a, b| a.total_cmp(b));
let median_width = widths[widths.len() / 2]; let median_width = widths[widths.len() / 2];
let width_threshold = median_width * 10.0; let width_threshold = median_width * 10.0;
let before = page_rects.len(); let before = page_rects.len();
@@ -333,7 +333,7 @@ pub fn detect_tables_from_rects(
// cluster they overlap, so grid detection still has their edges. // cluster they overlap, so grid detection still has their edges.
let is_page_bg = { let is_page_bg = {
let mut heights: Vec<f32> = page_rects.iter().map(|&(_, _, _, h)| h).collect(); let mut heights: Vec<f32> = page_rects.iter().map(|&(_, _, _, h)| h).collect();
heights.sort_by(|a, b| a.partial_cmp(b).unwrap_or(std::cmp::Ordering::Equal)); heights.sort_by(|a, b| a.total_cmp(b));
let median_height = heights[heights.len() / 2]; let median_height = heights[heights.len() / 2];
let height_threshold = median_height * 20.0; let height_threshold = median_height * 20.0;
let flags: Vec<bool> = page_rects let flags: Vec<bool> = page_rects
@@ -621,7 +621,7 @@ fn merge_overlapping_hints(mut hints: Vec<RectHintRegion>) -> Vec<RectHintRegion
return hints; return hints;
} }
loop { loop {
hints.sort_by(|a, b| a.x_left.partial_cmp(&b.x_left).unwrap()); hints.sort_by(|a, b| a.x_left.total_cmp(&b.x_left));
let mut merged: Vec<RectHintRegion> = Vec::new(); let mut merged: Vec<RectHintRegion> = Vec::new();
let mut any_merged = false; let mut any_merged = false;
for hint in &hints { for hint in &hints {
@@ -685,7 +685,7 @@ fn extract_hint_region(group_rects: &[(f32, f32, f32, f32)]) -> Option<RectHintR
// Compute median height to identify cell-sized rects // Compute median height to identify cell-sized rects
let mut heights: Vec<f32> = group_rects.iter().map(|&(_, _, _, h)| h).collect(); let mut heights: Vec<f32> = group_rects.iter().map(|&(_, _, _, h)| h).collect();
heights.sort_by(|a, b| a.partial_cmp(b).unwrap_or(std::cmp::Ordering::Equal)); heights.sort_by(|a, b| a.total_cmp(b));
let median_h = heights[heights.len() / 2]; let median_h = heights[heights.len() / 2];
// Keep only cell-sized rects (height ≤ 4× median) // Keep only cell-sized rects (height ≤ 4× median)
@@ -857,9 +857,9 @@ fn try_build_grid(
// Sort column edges left-to-right, row edges top-to-bottom (highest Y first for PDF) // Sort column edges left-to-right, row edges top-to-bottom (highest Y first for PDF)
let mut col_edges = x_edges; let mut col_edges = x_edges;
col_edges.sort_by(|a, b| a.partial_cmp(b).unwrap_or(std::cmp::Ordering::Equal)); col_edges.sort_by(|a, b| a.total_cmp(b));
let mut row_edges = y_edges; let mut row_edges = y_edges;
row_edges.sort_by(|a, b| b.partial_cmp(a).unwrap_or(std::cmp::Ordering::Equal)); row_edges.sort_by(|a, b| b.total_cmp(a));
let num_cols = col_edges.len() - 1; let num_cols = col_edges.len() - 1;
let num_rows = row_edges.len() - 1; let num_rows = row_edges.len() - 1;
@@ -1048,7 +1048,7 @@ fn try_build_grid(
/// Deduplicate nearby edge values within a tolerance, returning sorted unique edges. /// Deduplicate nearby edge values within a tolerance, returning sorted unique edges.
pub(crate) fn snap_edges(values: &[f32], tolerance: f32) -> Vec<f32> { pub(crate) fn snap_edges(values: &[f32], tolerance: f32) -> Vec<f32> {
let mut sorted: Vec<f32> = values.to_vec(); let mut sorted: Vec<f32> = values.to_vec();
sorted.sort_by(|a, b| a.partial_cmp(b).unwrap_or(std::cmp::Ordering::Equal)); sorted.sort_by(|a, b| a.total_cmp(b));
let mut snapped: Vec<f32> = Vec::new(); let mut snapped: Vec<f32> = Vec::new();
for &v in &sorted { for &v in &sorted {
@@ -1204,7 +1204,7 @@ fn is_row_stripe_pattern(rects: &[(f32, f32, f32, f32)]) -> bool {
} }
let mut widths: Vec<f32> = rects.iter().map(|&(_, _, w, _)| w).collect(); let mut widths: Vec<f32> = rects.iter().map(|&(_, _, w, _)| w).collect();
widths.sort_by(|a, b| a.partial_cmp(b).unwrap_or(std::cmp::Ordering::Equal)); widths.sort_by(|a, b| a.total_cmp(b));
let median_width = widths[widths.len() / 2]; let median_width = widths[widths.len() / 2];
// Must be page-spanning (>200pt) // Must be page-spanning (>200pt)
@@ -1252,7 +1252,7 @@ fn detect_row_stripe_table(
// Sort row edges top-to-bottom (highest Y first for PDF) // Sort row edges top-to-bottom (highest Y first for PDF)
let mut row_edges = y_edges; let mut row_edges = y_edges;
row_edges.sort_by(|a, b| b.partial_cmp(a).unwrap_or(std::cmp::Ordering::Equal)); row_edges.sort_by(|a, b| b.total_cmp(a));
// Compute the bounding box of the stripe region for filtering items // Compute the bounding box of the stripe region for filtering items
let y_top = row_edges[0]; let y_top = row_edges[0];
@@ -1476,7 +1476,7 @@ fn detect_row_stripe_table_from_cell_rects(
// bounding box to scope items and derive rows from text Y-positions. // bounding box to scope items and derive rows from text Y-positions.
let row_edges = if y_edges.len() >= 4 { let row_edges = if y_edges.len() >= 4 {
let mut edges = y_edges; let mut edges = y_edges;
edges.sort_by(|a, b| b.partial_cmp(a).unwrap_or(std::cmp::Ordering::Equal)); edges.sort_by(|a, b| b.total_cmp(a));
edges edges
} else { } else {
// Fall back: gather items in the rect region and cluster by Y // Fall back: gather items in the rect region and cluster by Y
@@ -1508,11 +1508,11 @@ fn detect_row_stripe_table_from_cell_rects(
// Cluster Y positions using median font height as threshold // Cluster Y positions using median font height as threshold
let median_h = { let median_h = {
let mut hs: Vec<f32> = region_items.iter().map(|i| i.height).collect(); let mut hs: Vec<f32> = region_items.iter().map(|i| i.height).collect();
hs.sort_by(|a, b| a.partial_cmp(b).unwrap_or(std::cmp::Ordering::Equal)); hs.sort_by(|a, b| a.total_cmp(b));
hs[hs.len() / 2] hs[hs.len() / 2]
}; };
let mut ys: Vec<f32> = region_items.iter().map(|i| i.y).collect(); let mut ys: Vec<f32> = region_items.iter().map(|i| i.y).collect();
ys.sort_by(|a, b| b.partial_cmp(a).unwrap_or(std::cmp::Ordering::Equal)); ys.sort_by(|a, b| b.total_cmp(a));
let mut edges = Vec::new(); let mut edges = Vec::new();
let threshold = median_h * 0.8; let threshold = median_h * 0.8;
let mut cluster_start = ys[0]; let mut cluster_start = ys[0];
@@ -1536,7 +1536,7 @@ fn detect_row_stripe_table_from_cell_rects(
edges.push(center - median_h * 0.5); edges.push(center - median_h * 0.5);
let _ = cluster_start; // suppress unused warning let _ = cluster_start; // suppress unused warning
edges = snap_edges(&edges, 3.0); edges = snap_edges(&edges, 3.0);
edges.sort_by(|a, b| b.partial_cmp(a).unwrap_or(std::cmp::Ordering::Equal)); edges.sort_by(|a, b| b.total_cmp(a));
if edges.len() < 4 { if edges.len() < 4 {
return None; return None;
} }
@@ -1546,7 +1546,7 @@ fn detect_row_stripe_table_from_cell_rects(
// Compute bounding box from non-full-page rects // Compute bounding box from non-full-page rects
let median_h = { let median_h = {
let mut heights: Vec<f32> = group_rects.iter().map(|&(_, _, _, h)| h).collect(); let mut heights: Vec<f32> = group_rects.iter().map(|&(_, _, _, h)| h).collect();
heights.sort_by(|a, b| a.partial_cmp(b).unwrap_or(std::cmp::Ordering::Equal)); heights.sort_by(|a, b| a.total_cmp(b));
heights[heights.len() / 2] heights[heights.len() / 2]
}; };
let content_rects: Vec<_> = group_rects let content_rects: Vec<_> = group_rects
@@ -1724,7 +1724,7 @@ fn detect_merged_cluster_table(
} }
let mut row_edges = y_edges; let mut row_edges = y_edges;
row_edges.sort_by(|a, b| b.partial_cmp(a).unwrap_or(std::cmp::Ordering::Equal)); row_edges.sort_by(|a, b| b.total_cmp(a));
// Bounding box of all rects // Bounding box of all rects
let y_top = row_edges[0]; let y_top = row_edges[0];
@@ -1890,7 +1890,7 @@ fn detect_merged_cluster_table(
/// (no need for anti-paragraph safeguards). /// (no need for anti-paragraph safeguards).
fn cluster_x_positions(items: &[(usize, &TextItem)], min_threshold: f32) -> Vec<f32> { fn cluster_x_positions(items: &[(usize, &TextItem)], min_threshold: f32) -> Vec<f32> {
let mut x_positions: Vec<f32> = items.iter().map(|(_, i)| i.x).collect(); let mut x_positions: Vec<f32> = items.iter().map(|(_, i)| i.x).collect();
x_positions.sort_by(|a, b| a.partial_cmp(b).unwrap_or(std::cmp::Ordering::Equal)); x_positions.sort_by(|a, b| a.total_cmp(b));
if x_positions.is_empty() { if x_positions.is_empty() {
return vec![]; return vec![];
src/tables/grid.rs
+4 -4
View File
@@ -9,7 +9,7 @@ pub(crate) fn find_column_boundaries(
mode: TableDetectionMode, mode: TableDetectionMode,
) -> Vec<f32> { ) -> Vec<f32> {
let mut x_positions: Vec<f32> = items.iter().map(|(_, i)| i.x).collect(); let mut x_positions: Vec<f32> = items.iter().map(|(_, i)| i.x).collect();
x_positions.sort_by(|a, b| a.partial_cmp(b).unwrap_or(std::cmp::Ordering::Equal)); x_positions.sort_by(|a, b| a.total_cmp(b));
if x_positions.is_empty() { if x_positions.is_empty() {
return vec![]; return vec![];
@@ -43,7 +43,7 @@ pub(crate) fn find_column_boundaries(
.collect(); .collect();
if consec_gaps.len() > 2 { if consec_gaps.len() > 2 {
consec_gaps.sort_by(|a, b| a.partial_cmp(b).unwrap()); consec_gaps.sort_by(|a, b| a.total_cmp(b));
// Find the biggest jump in the sorted gap sequence — natural break // Find the biggest jump in the sorted gap sequence — natural break
// between within-column jitter and between-column spacing. // between within-column jitter and between-column spacing.
// Require at least 3 values on each side to avoid outlier-dominated // Require at least 3 values on each side to avoid outlier-dominated
@@ -151,7 +151,7 @@ pub(crate) fn find_column_boundaries(
/// Find row boundaries by clustering Y positions /// Find row boundaries by clustering Y positions
pub(crate) fn find_row_boundaries(items: &[(usize, &TextItem)]) -> Vec<f32> { pub(crate) fn find_row_boundaries(items: &[(usize, &TextItem)]) -> Vec<f32> {
let mut y_positions: Vec<f32> = items.iter().map(|(_, i)| i.y).collect(); let mut y_positions: Vec<f32> = items.iter().map(|(_, i)| i.y).collect();
y_positions.sort_by(|a, b| b.partial_cmp(a).unwrap_or(std::cmp::Ordering::Equal)); // Descending y_positions.sort_by(|a, b| b.total_cmp(a)); // Descending
if y_positions.is_empty() { if y_positions.is_empty() {
return vec![]; return vec![];
@@ -162,7 +162,7 @@ pub(crate) fn find_row_boundaries(items: &[(usize, &TextItem)]) -> Vec<f32> {
// inter-row gaps (≥1× font size), preventing row merging in uniform-spaced PDFs. // inter-row gaps (≥1× font size), preventing row merging in uniform-spaced PDFs.
let cluster_threshold = { let cluster_threshold = {
let mut font_sizes: Vec<f32> = items.iter().map(|(_, i)| i.font_size).collect(); let mut font_sizes: Vec<f32> = items.iter().map(|(_, i)| i.font_size).collect();
font_sizes.sort_by(|a, b| a.partial_cmp(b).unwrap_or(std::cmp::Ordering::Equal)); font_sizes.sort_by(|a, b| a.total_cmp(b));
let median_font = font_sizes[font_sizes.len() / 2]; let median_font = font_sizes[font_sizes.len() / 2];
(median_font * 0.8).max(4.0) (median_font * 0.8).max(4.0)
}; };
src/tables/mod.rs
+6 -6
View File
@@ -33,7 +33,7 @@ pub(crate) fn try_build_rect_guided_table(
// 1. Derive column boundaries from rect X positions (snapped to 2pt tolerance) // 1. Derive column boundaries from rect X positions (snapped to 2pt tolerance)
let mut x_lefts: Vec<f32> = cluster_rects.iter().map(|&(x, _, _, _)| x).collect(); let mut x_lefts: Vec<f32> = cluster_rects.iter().map(|&(x, _, _, _)| x).collect();
x_lefts.sort_by(|a, b| a.partial_cmp(b).unwrap_or(std::cmp::Ordering::Equal)); x_lefts.sort_by(|a, b| a.total_cmp(b));
// Snap: deduplicate within 2pt tolerance // Snap: deduplicate within 2pt tolerance
let mut col_boundaries: Vec<f32> = Vec::new(); let mut col_boundaries: Vec<f32> = Vec::new();
for x in &x_lefts { for x in &x_lefts {
@@ -54,7 +54,7 @@ pub(crate) fn try_build_rect_guided_table(
// boundaries so every day gets a column. // boundaries so every day gets a column.
if col_boundaries.len() >= 2 { if col_boundaries.len() >= 2 {
let mut spacings: Vec<f32> = col_boundaries.windows(2).map(|w| w[1] - w[0]).collect(); let mut spacings: Vec<f32> = col_boundaries.windows(2).map(|w| w[1] - w[0]).collect();
spacings.sort_by(|a, b| a.partial_cmp(b).unwrap_or(std::cmp::Ordering::Equal)); spacings.sort_by(|a, b| a.total_cmp(b));
let median_spacing = spacings[spacings.len() / 2]; let median_spacing = spacings[spacings.len() / 2];
let threshold = median_spacing * 1.5; let threshold = median_spacing * 1.5;
@@ -87,7 +87,7 @@ pub(crate) fn try_build_rect_guided_table(
// 3. Derive row boundaries from item Y positions (5pt tolerance) // 3. Derive row boundaries from item Y positions (5pt tolerance)
let mut y_values: Vec<f32> = expanded_items.iter().map(|(item, _)| item.y).collect(); let mut y_values: Vec<f32> = expanded_items.iter().map(|(item, _)| item.y).collect();
y_values.sort_by(|a, b| b.partial_cmp(a).unwrap_or(std::cmp::Ordering::Equal)); // descending y_values.sort_by(|a, b| b.total_cmp(a)); // descending
let mut row_boundaries: Vec<f32> = Vec::new(); let mut row_boundaries: Vec<f32> = Vec::new();
for y in &y_values { for y in &y_values {
if row_boundaries if row_boundaries
@@ -296,7 +296,7 @@ pub(crate) fn try_build_table_from_columns(items: &[TextItem], page: u32) -> Opt
// Find the top-most row with items in multiple columns (likely the header) // Find the top-most row with items in multiple columns (likely the header)
let mut ys: Vec<f32> = page_items.iter().map(|i| i.y).collect(); let mut ys: Vec<f32> = page_items.iter().map(|i| i.y).collect();
ys.sort_by(|a, b| b.partial_cmp(a).unwrap_or(std::cmp::Ordering::Equal)); ys.sort_by(|a, b| b.total_cmp(a));
ys.dedup_by(|a, b| (*a - *b).abs() < y_tol); ys.dedup_by(|a, b| (*a - *b).abs() < y_tol);
for &header_y in ys.iter().take(5) { for &header_y in ys.iter().take(5) {
@@ -318,7 +318,7 @@ pub(crate) fn try_build_table_from_columns(items: &[TextItem], page: u32) -> Opt
if col_items.len() >= 2 { if col_items.len() >= 2 {
// Sort by X and find the split point // Sort by X and find the split point
let mut sorted: Vec<f32> = col_items.iter().map(|i| i.x).collect(); let mut sorted: Vec<f32> = col_items.iter().map(|i| i.x).collect();
sorted.sort_by(|a, b| a.partial_cmp(b).unwrap_or(std::cmp::Ordering::Equal)); sorted.sort_by(|a, b| a.total_cmp(b));
// Split at the midpoint between the two items // Split at the midpoint between the two items
let split_x = (sorted[0] let split_x = (sorted[0]
+ col_items.iter().find(|i| i.x == sorted[0]).unwrap().width + col_items.iter().find(|i| i.x == sorted[0]).unwrap().width
@@ -411,7 +411,7 @@ pub(crate) fn try_build_table_from_columns(items: &[TextItem], page: u32) -> Opt
} }
} }
} }
row_ys.sort_by(|a, b| b.partial_cmp(a).unwrap_or(std::cmp::Ordering::Equal)); row_ys.sort_by(|a, b| b.total_cmp(a));
if row_ys.len() < 3 || row_ys.len() > 40 { if row_ys.len() < 3 || row_ys.len() > 40 {
return None; return None;
src/text_utils.rs
+4 -4
View File
@@ -68,9 +68,9 @@ where
pub(crate) fn sort_line_items(items: &mut [TextItem]) { pub(crate) fn sort_line_items(items: &mut [TextItem]) {
let rtl = is_rtl_text(items.iter().map(|i| &i.text)); let rtl = is_rtl_text(items.iter().map(|i| &i.text));
if rtl { if rtl {
items.sort_by(|a, b| b.x.partial_cmp(&a.x).unwrap_or(std::cmp::Ordering::Equal)); items.sort_by(|a, b| b.x.total_cmp(&a.x));
} else { } else {
items.sort_by(|a, b| a.x.partial_cmp(&b.x).unwrap_or(std::cmp::Ordering::Equal)); items.sort_by(|a, b| a.x.total_cmp(&b.x));
} }
} }
@@ -376,7 +376,7 @@ fn compute_canva_join_threshold(items: &[TextItem]) -> f32 {
} }
let mut sorted: Vec<f32> = ratios; let mut sorted: Vec<f32> = ratios;
sorted.sort_by(|a, b| a.partial_cmp(b).unwrap_or(std::cmp::Ordering::Equal)); sorted.sort_by(|a, b| a.total_cmp(b));
if sorted[sorted.len() - 1] < 0.40 || sorted[0] < 0.40 { if sorted[sorted.len() - 1] < 0.40 || sorted[0] < 0.40 {
return DEFAULT; return DEFAULT;
@@ -478,7 +478,7 @@ fn compute_single_char_join_threshold(items: &[TextItem]) -> f32 {
return DEFAULT; return DEFAULT;
} }
ratios.sort_by(|a, b| a.partial_cmp(b).unwrap_or(std::cmp::Ordering::Equal)); ratios.sort_by(|a, b| a.total_cmp(b));
// If all gaps are tight (max < 0.40), use default — normal PDF // If all gaps are tight (max < 0.40), use default — normal PDF
let max_ratio = ratios[ratios.len() - 1]; let max_ratio = ratios[ratios.len() - 1];