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

add ci, plus new package

Browse Source
This commit is contained in:
Abimael Martell
2026-02-06 21:39:21 -08:00
parent ee09e96cc4
commit 0ef7b2adfc
10 changed files with 279 additions and 99 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.github/workflows/ci.yml
+105
View File
@@ -0,0 +1,105 @@
name: CI
on:
push:
branches: [main]
pull_request:
branches: [main]
env:
CARGO_TERM_COLOR: always
jobs:
test:
name: Test
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- name: Install Rust
uses: dtolnay/rust-action@stable
- name: Cache cargo
uses: actions/cache@v4
with:
path: |
~/.cargo/bin/
~/.cargo/registry/index/
~/.cargo/registry/cache/
~/.cargo/git/db/
target/
key: ${{ runner.os }}-cargo-${{ hashFiles('**/Cargo.lock') }}
restore-keys: |
${{ runner.os }}-cargo-
- name: Run tests
run: cargo test --verbose
fmt:
name: Format
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- name: Install Rust
uses: dtolnay/rust-action@stable
with:
components: rustfmt
- name: Check formatting
run: cargo fmt --all -- --check
clippy:
name: Clippy
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- name: Install Rust
uses: dtolnay/rust-action@stable
with:
components: clippy
- name: Cache cargo
uses: actions/cache@v4
with:
path: |
~/.cargo/bin/
~/.cargo/registry/index/
~/.cargo/registry/cache/
~/.cargo/git/db/
target/
key: ${{ runner.os }}-cargo-clippy-${{ hashFiles('**/Cargo.lock') }}
restore-keys: |
${{ runner.os }}-cargo-clippy-
- name: Run clippy
run: cargo clippy -- -D warnings
build:
name: Build
runs-on: ${{ matrix.os }}
strategy:
matrix:
os: [ubuntu-latest, macos-latest]
steps:
- uses: actions/checkout@v4
- name: Install Rust
uses: dtolnay/rust-action@stable
- name: Cache cargo
uses: actions/cache@v4
with:
path: |
~/.cargo/bin/
~/.cargo/registry/index/
~/.cargo/registry/cache/
~/.cargo/git/db/
target/
key: ${{ runner.os }}-cargo-build-${{ hashFiles('**/Cargo.lock') }}
restore-keys: |
${{ runner.os }}-cargo-build-
- name: Build
run: cargo build --release --verbose
Cargo.toml
+3 -2
View File
@@ -1,10 +1,11 @@
[package]
name = "pdf-to-markdown"
name = "pdf-inspector"
version = "0.1.0"
edition = "2021"
authors = ["Firecrawl Team"]
description = "Fast PDF to Markdown conversion with smart detection"
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
README.md
+14 -14
View File
@@ -1,6 +1,6 @@
# pdf-to-markdown
# pdf-inspector
Fast Rust library for PDF to Markdown conversion with smart scanned vs text-based detection.
Fast Rust library for PDF inspection, classification, and text extraction. Intelligently detects scanned vs text-based PDFs to enable smart routing decisions.
## Features
@@ -15,7 +15,7 @@ Add to your `Cargo.toml`:
```toml
[dependencies]
pdf-to-markdown = "0.1"
pdf-inspector = { git = "https://github.com/firecrawl/pdf-inspector" }
```
## Usage
@@ -25,16 +25,16 @@ pdf-to-markdown = "0.1"
The simplest way to convert a PDF to Markdown:
```rust
use pdf_to_markdown::process_pdf;
use pdf_inspector::process_pdf;
fn main() -> Result<(), Box<dyn std::error::Error>> {
let result = process_pdf("document.pdf")?;
match result.pdf_type {
pdf_to_markdown::PdfType::TextBased => {
pdf_inspector::PdfType::TextBased => {
println!("Markdown:\n{}", result.markdown.unwrap());
}
pdf_to_markdown::PdfType::Scanned => {
pdf_inspector::PdfType::Scanned => {
println!("PDF is scanned - OCR required");
}
_ => {}
@@ -49,7 +49,7 @@ fn main() -> Result<(), Box<dyn std::error::Error>> {
Quickly detect if a PDF is text-based or scanned without full extraction:
```rust
use pdf_to_markdown::{detect_pdf_type, PdfType};
use pdf_inspector::{detect_pdf_type, PdfType};
fn main() -> Result<(), Box<dyn std::error::Error>> {
let result = detect_pdf_type("document.pdf")?;
@@ -78,7 +78,7 @@ fn main() -> Result<(), Box<dyn std::error::Error>> {
Extract plain text from a PDF:
```rust
use pdf_to_markdown::extract_text;
use pdf_inspector::extract_text;
fn main() -> Result<(), Box<dyn std::error::Error>> {
let text = extract_text("document.pdf")?;
@@ -92,8 +92,8 @@ fn main() -> Result<(), Box<dyn std::error::Error>> {
Get text items with position data for advanced processing:
```rust
use pdf_to_markdown::{extract_text_with_positions, TextItem};
use pdf_to_markdown::extractor::group_into_lines;
use pdf_inspector::{extract_text_with_positions, TextItem};
use pdf_inspector::extractor::group_into_lines;
fn main() -> Result<(), Box<dyn std::error::Error>> {
let items = extract_text_with_positions("document.pdf")?;
@@ -118,7 +118,7 @@ fn main() -> Result<(), Box<dyn std::error::Error>> {
Convert text to Markdown with custom options:
```rust
use pdf_to_markdown::{to_markdown, MarkdownOptions};
use pdf_inspector::{to_markdown, MarkdownOptions};
fn main() {
let text = "• First item\n• Second item\n\nconst x = 5;";
@@ -144,8 +144,8 @@ fn main() {
All functions have memory buffer variants for processing PDFs already in memory:
```rust
use pdf_to_markdown::{process_pdf_mem, detector::detect_pdf_type_mem};
use pdf_to_markdown::extractor::{extract_text_mem, extract_text_with_positions_mem};
use pdf_inspector::{process_pdf_mem, detector::detect_pdf_type_mem};
use pdf_inspector::extractor::{extract_text_mem, extract_text_with_positions_mem};
fn main() -> Result<(), Box<dyn std::error::Error>> {
let buffer = std::fs::read("document.pdf")?;
@@ -168,7 +168,7 @@ fn main() -> Result<(), Box<dyn std::error::Error>> {
Fine-tune the detection algorithm:
```rust
use pdf_to_markdown::detector::{detect_pdf_type_with_config, DetectionConfig};
use pdf_inspector::detector::{detect_pdf_type_with_config, DetectionConfig};
fn main() -> Result<(), Box<dyn std::error::Error>> {
let config = DetectionConfig {
src/bin/detect_pdf.rs
+9 -3
View File
@@ -1,6 +1,6 @@
//! CLI tool for detecting PDF type (text-based vs scanned)
use pdf_to_markdown::{detect_pdf_type, PdfType};
use pdf_inspector::{detect_pdf_type, PdfType};
use std::env;
use std::process;
use std::time::Instant;
@@ -36,7 +36,11 @@ fn main() {
result.pages_sampled,
result.pages_with_text,
result.confidence,
result.title.as_ref().map(|t| format!("\"{}\"", t.replace('"', "\\\""))).unwrap_or_else(|| "null".to_string()),
result
.title
.as_ref()
.map(|t| format!("\"{}\"", t.replace('"', "\\\"")))
.unwrap_or_else(|| "null".to_string()),
elapsed.as_millis()
);
} else {
@@ -77,7 +81,9 @@ fn main() {
println!("Recommendation: Use OCR for best results");
}
PdfType::Mixed => {
println!("Recommendation: Try text extraction first, use OCR for image pages");
println!(
"Recommendation: Try text extraction first, use OCR for image pages"
);
}
}
}
src/bin/pdf2md.rs
+6 -2
View File
@@ -1,6 +1,6 @@
//! CLI tool for PDF to Markdown conversion
use pdf_to_markdown::{process_pdf, PdfType};
use pdf_inspector::{process_pdf, PdfType};
use std::env;
use std::fs;
use std::process;
@@ -32,7 +32,11 @@ fn main() {
let md_escaped = result
.markdown
.as_ref()
.map(|m| m.replace('\\', "\\\\").replace('"', "\\\"").replace('\n', "\\n"))
.map(|m| {
m.replace('\\', "\\\\")
.replace('"', "\\\"")
.replace('\n', "\\n")
})
.unwrap_or_default();
println!(
src/detector.rs
+5 -10
View File
@@ -263,19 +263,14 @@ fn scan_content_for_text_operators(content: &[u8]) -> (u32, bool) {
}
}
// Look for BT (Begin Text) as additional confirmation
if b == b'B' && i + 1 < content.len() && content[i + 1] == b'T' {
if i + 2 >= content.len() || content[i + 2].is_ascii_whitespace() {
// BT found - text block marker
}
}
// Look for 'Do' operator (XObject/image placement)
if b == b'D' && i + 1 < content.len() && content[i + 1] == b'o' {
if i + 2 >= content.len() || content[i + 2].is_ascii_whitespace() {
if b == b'D'
&& i + 1 < content.len()
&& content[i + 1] == b'o'
&& (i + 2 >= content.len() || content[i + 2].is_ascii_whitespace())
{
has_images = true;
}
}
i += 1;
}
src/extractor.rs
+22 -10
View File
@@ -37,7 +37,11 @@ pub struct TextLine {
impl TextLine {
pub fn text(&self) -> String {
self.items.iter().map(|i| i.text.as_str()).collect::<Vec<_>>().join(" ")
self.items
.iter()
.map(|i| i.text.as_str())
.collect::<Vec<_>>()
.join(" ")
}
}
@@ -101,11 +105,11 @@ fn extract_page_text_items(
let fonts = doc.get_page_fonts(page_id).unwrap_or_default();
// Get content
let content_data = doc.get_page_content(page_id)
let content_data = doc
.get_page_content(page_id)
.map_err(|e| PdfError::Parse(e.to_string()))?;
let content = Content::decode(&content_data)
.map_err(|e| PdfError::Parse(e.to_string()))?;
let content = Content::decode(&content_data).map_err(|e| PdfError::Parse(e.to_string()))?;
// Text state tracking
let mut current_font = String::new();
@@ -153,7 +157,8 @@ fn extract_page_text_items(
// Set text matrix
if op.operands.len() >= 6 {
for (i, operand) in op.operands.iter().take(6).enumerate() {
text_matrix[i] = get_number(operand).unwrap_or(if i == 0 || i == 3 { 1.0 } else { 0.0 });
text_matrix[i] =
get_number(operand).unwrap_or(if i == 0 || i == 3 { 1.0 } else { 0.0 });
}
line_matrix = text_matrix;
}
@@ -166,7 +171,9 @@ fn extract_page_text_items(
"Tj" => {
// Show text string
if in_text_block && !op.operands.is_empty() {
if let Some(text) = extract_text_from_operand(&op.operands[0], doc, &fonts, &current_font) {
if let Some(text) =
extract_text_from_operand(&op.operands[0], doc, &fonts, &current_font)
{
if !text.trim().is_empty() {
items.push(TextItem {
text,
@@ -188,7 +195,9 @@ fn extract_page_text_items(
if let Ok(array) = op.operands[0].as_array() {
let mut combined_text = String::new();
for item in array {
if let Some(text) = extract_text_from_operand(item, doc, &fonts, &current_font) {
if let Some(text) =
extract_text_from_operand(item, doc, &fonts, &current_font)
{
combined_text.push_str(&text);
}
}
@@ -212,7 +221,9 @@ fn extract_page_text_items(
line_matrix[5] -= current_font_size * 1.2;
text_matrix = line_matrix;
if !op.operands.is_empty() {
if let Some(text) = extract_text_from_operand(&op.operands[0], doc, &fonts, &current_font) {
if let Some(text) =
extract_text_from_operand(&op.operands[0], doc, &fonts, &current_font)
{
if !text.trim().is_empty() {
items.push(TextItem {
text,
@@ -239,7 +250,7 @@ fn extract_page_text_items(
fn get_number(obj: &Object) -> Option<f32> {
match obj {
Object::Integer(i) => Some(*i as f32),
Object::Real(r) => Some(*r as f32),
Object::Real(r) => Some(*r),
_ => None,
}
}
@@ -286,7 +297,8 @@ pub fn group_into_lines(items: Vec<TextItem>) -> Vec<TextLine> {
// Sort by page, then by Y (descending for PDF coords), then by X
let mut sorted = items;
sorted.sort_by(|a, b| {
a.page.cmp(&b.page)
a.page
.cmp(&b.page)
.then(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))
});
src/lib.rs
+8 -6
View File
@@ -69,7 +69,9 @@ pub fn process_pdf<P: AsRef<Path>>(path: P) -> Result<PdfProcessResult, PdfError
PdfType::Mixed => {
// Try to extract what we can
let text = extract_text(&path).ok();
let markdown = text.as_ref().map(|t| to_markdown(t, MarkdownOptions::default()));
let markdown = text
.as_ref()
.map(|t| to_markdown(t, MarkdownOptions::default()));
PdfProcessResult {
pdf_type: PdfType::Mixed,
@@ -105,18 +107,18 @@ pub fn process_pdf_mem(buffer: &[u8]) -> Result<PdfProcessResult, PdfError> {
processing_time_ms: start.elapsed().as_millis() as u64,
}
}
PdfType::Scanned | PdfType::ImageBased => {
PdfProcessResult {
PdfType::Scanned | PdfType::ImageBased => PdfProcessResult {
pdf_type: detection.pdf_type,
text: None,
markdown: None,
page_count: detection.page_count,
processing_time_ms: start.elapsed().as_millis() as u64,
}
}
},
PdfType::Mixed => {
let text = extractor::extract_text_mem(buffer).ok();
let markdown = text.as_ref().map(|t| to_markdown(t, MarkdownOptions::default()));
let markdown = text
.as_ref()
.map(|t| to_markdown(t, MarkdownOptions::default()));
PdfProcessResult {
pdf_type: PdfType::Mixed,
src/markdown.rs
+39 -13
View File
@@ -6,7 +6,7 @@
//! - Code blocks (monospace fonts, indentation)
//! - Paragraphs
use crate::extractor::{TextItem, TextLine, group_into_lines};
use crate::extractor::{group_into_lines, TextItem, TextLine};
use std::collections::HashMap;
/// Options for markdown conversion
@@ -103,7 +103,9 @@ pub fn to_markdown_from_lines(lines: Vec<TextLine>, options: MarkdownOptions) ->
// Calculate font statistics
let font_stats = calculate_font_stats(&lines);
let base_size = options.base_font_size.unwrap_or(font_stats.most_common_size);
let base_size = options
.base_font_size
.unwrap_or(font_stats.most_common_size);
let mut output = String::new();
let mut current_page = 0u32;
@@ -201,9 +203,7 @@ fn calculate_font_stats(lines: &[TextLine]) -> FontStats {
.map(|(size, _)| *size as f32 / 10.0)
.unwrap_or(12.0);
FontStats {
most_common_size,
}
FontStats { most_common_size }
}
/// Detect header level from font size
@@ -242,7 +242,7 @@ fn is_list_item(text: &str) -> bool {
let first_chars: String = trimmed.chars().take(5).collect();
if first_chars.contains(|c: char| c.is_ascii_digit()) {
// Check for "1.", "1)", "10."
if let Some(idx) = first_chars.find(|c: char| c == '.' || c == ')') {
if let Some(idx) = first_chars.find(['.', ')']) {
let prefix = &first_chars[..idx];
if prefix.chars().all(|c| c.is_ascii_digit()) {
return true;
@@ -292,10 +292,24 @@ fn is_code_like(text: &str) -> bool {
// Code patterns
let code_patterns = [
// Language keywords
"import ", "export ", "from ", "const ", "let ", "var ", "function ",
"class ", "def ", "pub fn ", "fn ", "async fn ", "impl ",
"import ",
"export ",
"from ",
"const ",
"let ",
"var ",
"function ",
"class ",
"def ",
"pub fn ",
"fn ",
"async fn ",
"impl ",
// Syntax patterns
"=> ", "-> ", ":: ", ":= ",
"=> ",
"-> ",
":: ",
":= ",
// Common code endings
];
@@ -306,7 +320,8 @@ fn is_code_like(text: &str) -> bool {
}
// Check for code-like syntax
let special_chars: usize = trimmed.chars()
let special_chars: usize = trimmed
.chars()
.filter(|c| matches!(c, '{' | '}' | '(' | ')' | '[' | ']' | ';' | '=' | '<' | '>'))
.count();
@@ -326,9 +341,20 @@ fn is_code_like(text: &str) -> bool {
fn is_monospace_font(font_name: &str) -> bool {
let lower = font_name.to_lowercase();
let patterns = [
"courier", "consolas", "monaco", "menlo", "mono", "fixed",
"terminal", "typewriter", "source code", "fira code",
"jetbrains", "inconsolata", "dejavu sans mono", "liberation mono",
"courier",
"consolas",
"monaco",
"menlo",
"mono",
"fixed",
"terminal",
"typewriter",
"source code",
"fira code",
"jetbrains",
"inconsolata",
"dejavu sans mono",
"liberation mono",
];
patterns.iter().any(|p| lower.contains(p))
tests/integration_tests.rs
+57 -28
View File
@@ -1,11 +1,11 @@
//! Integration tests for pdf-to-markdown library
use pdf_to_markdown::{
detect_pdf_type, extract_text, extract_text_with_positions, to_markdown,
MarkdownOptions, PdfType, TextItem,
use pdf_inspector::detector::DetectionConfig;
use pdf_inspector::extractor::{group_into_lines, TextLine};
use pdf_inspector::{
detect_pdf_type, extract_text, extract_text_with_positions, to_markdown, MarkdownOptions,
PdfType, TextItem,
};
use pdf_to_markdown::detector::DetectionConfig;
use pdf_to_markdown::extractor::{group_into_lines, TextLine};
// Helper to create test TextItems
fn make_text_item(text: &str, x: f32, y: f32, font_size: f32, page: u32) -> TextItem {
@@ -21,7 +21,14 @@ fn make_text_item(text: &str, x: f32, y: f32, font_size: f32, page: u32) -> Text
}
}
fn make_text_item_with_font(text: &str, x: f32, y: f32, font_size: f32, font: &str, page: u32) -> TextItem {
fn make_text_item_with_font(
text: &str,
x: f32,
y: f32,
font_size: f32,
font: &str,
page: u32,
) -> TextItem {
TextItem {
text: text.to_string(),
x,
@@ -347,7 +354,7 @@ fn test_to_markdown_whitespace_only_lines() {
#[test]
fn test_markdown_from_items_empty() {
use pdf_to_markdown::markdown::to_markdown_from_items;
use pdf_inspector::markdown::to_markdown_from_items;
let items: Vec<TextItem> = vec![];
let md = to_markdown_from_items(items, MarkdownOptions::default());
assert!(md.is_empty());
@@ -355,7 +362,7 @@ fn test_markdown_from_items_empty() {
#[test]
fn test_markdown_from_items_single() {
use pdf_to_markdown::markdown::to_markdown_from_items;
use pdf_inspector::markdown::to_markdown_from_items;
let items = vec![make_text_item("Hello", 100.0, 700.0, 12.0, 1)];
let md = to_markdown_from_items(items, MarkdownOptions::default());
assert!(md.contains("Hello"));
@@ -363,7 +370,7 @@ fn test_markdown_from_items_single() {
#[test]
fn test_markdown_from_items_header_detection() {
use pdf_to_markdown::markdown::to_markdown_from_items;
use pdf_inspector::markdown::to_markdown_from_items;
// Need multiple body items to establish base font size
let items = vec![
make_text_item("Title", 100.0, 750.0, 24.0, 1), // Large font = H1
@@ -378,10 +385,13 @@ fn test_markdown_from_items_header_detection() {
#[test]
fn test_markdown_from_items_h2_detection() {
use pdf_to_markdown::markdown::to_markdown_from_items;
use pdf_inspector::markdown::to_markdown_from_items;
// Need multiple body items to establish base font size
let items = vec![
make_text_item("Subtitle", 100.0, 750.0, 18.0, 1), // 1.5x = H2
make_text_item("Body text", 100.0, 700.0, 12.0, 1),
make_text_item("Body text one", 100.0, 700.0, 12.0, 1),
make_text_item("Body text two", 100.0, 680.0, 12.0, 1),
make_text_item("Body text three", 100.0, 660.0, 12.0, 1),
];
let md = to_markdown_from_items(items, MarkdownOptions::default());
assert!(md.contains("## Subtitle"));
@@ -389,10 +399,15 @@ fn test_markdown_from_items_h2_detection() {
#[test]
fn test_markdown_from_items_monospace_code() {
use pdf_to_markdown::markdown::to_markdown_from_items;
let items = vec![
make_text_item_with_font("let x = 5", 100.0, 700.0, 12.0, "Courier", 1),
];
use pdf_inspector::markdown::to_markdown_from_items;
let items = vec![make_text_item_with_font(
"let x = 5",
100.0,
700.0,
12.0,
"Courier",
1,
)];
let md = to_markdown_from_items(items, MarkdownOptions::default());
assert!(md.contains("```"));
assert!(md.contains("let x = 5"));
@@ -400,7 +415,7 @@ fn test_markdown_from_items_monospace_code() {
#[test]
fn test_markdown_from_items_page_breaks() {
use pdf_to_markdown::markdown::to_markdown_from_items;
use pdf_inspector::markdown::to_markdown_from_items;
let items = vec![
make_text_item("Page 1", 100.0, 700.0, 12.0, 1),
make_text_item("Page 2", 100.0, 700.0, 12.0, 2),
@@ -415,7 +430,7 @@ fn test_markdown_from_items_page_breaks() {
#[test]
fn test_markdown_from_lines_empty() {
use pdf_to_markdown::markdown::to_markdown_from_lines;
use pdf_inspector::markdown::to_markdown_from_lines;
let lines: Vec<TextLine> = vec![];
let md = to_markdown_from_lines(lines, MarkdownOptions::default());
assert!(md.is_empty());
@@ -423,7 +438,7 @@ fn test_markdown_from_lines_empty() {
#[test]
fn test_markdown_from_lines_basic() {
use pdf_to_markdown::markdown::to_markdown_from_lines;
use pdf_inspector::markdown::to_markdown_from_lines;
let lines = vec![
TextLine {
items: vec![make_text_item("First", 100.0, 700.0, 12.0, 1)],
@@ -557,18 +572,32 @@ fn test_non_code_text() {
#[test]
fn test_monospace_font_names() {
use pdf_to_markdown::markdown::to_markdown_from_items;
use pdf_inspector::markdown::to_markdown_from_items;
// Font names that contain the patterns in is_monospace_font
let monospace_fonts = [
"Courier", "Consolas", "Monaco", "Menlo",
"Fira Code", "JetBrains Mono", "Inconsolata",
"DejaVu Sans Mono", "Liberation Mono", "Fixed", "Terminal",
"Courier",
"Consolas",
"Monaco",
"Menlo",
"Fira Code",
"JetBrains Mono",
"Inconsolata",
"DejaVu Sans Mono",
"Liberation Mono",
"Fixed",
"Terminal",
];
for font in &monospace_fonts {
let items = vec![make_text_item_with_font("code", 100.0, 700.0, 12.0, font, 1)];
let items = vec![make_text_item_with_font(
"code", 100.0, 700.0, 12.0, font, 1,
)];
let md = to_markdown_from_items(items, MarkdownOptions::default());
assert!(md.contains("```"), "Font not detected as monospace: {}", font);
assert!(
md.contains("```"),
"Font not detected as monospace: {}",
font
);
}
}
@@ -578,7 +607,7 @@ fn test_monospace_font_names() {
#[test]
fn test_header_level_h1() {
use pdf_to_markdown::markdown::to_markdown_from_items;
use pdf_inspector::markdown::to_markdown_from_items;
// 24.0 / 12.0 = 2.0x = H1
// Need multiple body items to establish base font size
let items = vec![
@@ -593,7 +622,7 @@ fn test_header_level_h1() {
#[test]
fn test_header_level_h2() {
use pdf_to_markdown::markdown::to_markdown_from_items;
use pdf_inspector::markdown::to_markdown_from_items;
// 18.0 / 12.0 = 1.5x = H2
// Need multiple body items to establish base font size
let items = vec![
@@ -608,7 +637,7 @@ fn test_header_level_h2() {
#[test]
fn test_header_level_h3() {
use pdf_to_markdown::markdown::to_markdown_from_items;
use pdf_inspector::markdown::to_markdown_from_items;
// 15.0 / 12.0 = 1.25x = H3
// Need multiple body items to establish base font size
let items = vec![
@@ -623,7 +652,7 @@ fn test_header_level_h3() {
#[test]
fn test_header_level_h4() {
use pdf_to_markdown::markdown::to_markdown_from_items;
use pdf_inspector::markdown::to_markdown_from_items;
// 13.5 / 12.0 = 1.125x = H4 (>= 1.1)
// Need multiple body items to establish base font size
let items = vec![