refactor(vision): expose OCR API

Cargo.toml

@@ -86,6 +86,9 @@ model-cache = ["vision", "dep:dirs", "dep:fs2", "dep:sha2", "dep:windows-sys"]
 model-download = ["model-cache", "dep:ureq"]
 ocr-oar = ["model-cache", "dep:image", "dep:oar-ocr", "dep:ort"]
 render-pdfium = ["vision", "dep:firecrawl-pdfium"]
+# Complete native OCR path. This remains opt-in so default library,
+# renderer-only, and browser consumers do not inherit inference or HTTP/TLS.
+ocr = ["render-pdfium", "ocr-oar", "model-download"]
 
 [[bin]]
 name = "pdf2md"

docs/rust-api.md

@@ -340,6 +340,62 @@ warnings. A page that required OCR recommends the hosted pipeline when local
 OCR is missing, empty, or below the configurable page-confidence threshold.
 This keeps the lightweight path explicit about cases it cannot finish well.
 
+### Complete OCR API
+
+The `ocr` convenience feature enables the renderer, OCR engine, verified
+model acquisition, routing, and fusion layers together. It is the intended
+downstream application integration boundary; lower-level features remain
+available for consumers that bring their own renderer, model package manager,
+or engine.
+
+```toml
+[dependencies]
+pdf-inspector = { version = "1", features = ["ocr"] }
+```
+
+```rust
+use pdf_inspector::vision::{
+    process_pdf_with_ocr, OcrMode, OcrPdfOptions,
+};
+
+let result = process_pdf_with_ocr(
+    "document.pdf",
+    OcrPdfOptions::new()
+        .mode(OcrMode::Auto)
+        .pages([1, 2, 3]),
+)?;
+
+println!("{}", result.markdown);
+println!("OCR pages: {:?}", result.pages_routed_to_ocr);
+println!(
+    "Hosted fallback pages: {:?}",
+    result.pages_recommending_hosted,
+);
+```
+
+Native extraction always runs first. In `Auto`, a clean PDF returns before
+PDFium loading, model-cache access, HTTP, or OAR initialization. Model files
+remain external and the default crate feature set remains unchanged. `Off`
+provides the same native-only behavior through the OCR result/provenance
+shape; `Force` renders every selected page. Learned layout intentionally
+returns an explicit unsupported error in this lightweight pipeline.
+
+Build the CLI with the same opt-in feature:
+
+```bash
+cargo build --release --features ocr --bin pdf2md
+pdf2md document.pdf --ocr auto --raw
+pdf2md document.pdf --ocr auto --json
+pdf2md document.pdf --ocr auto --ocr-offline --ocr-model-dir /opt/models/pp-ocrv6-small
+```
+
+CLI controls include `--ocr-dpi`, `--ocr-min-confidence`,
+`--ocr-hosted-threshold`, `--select-pages`, and the existing encrypted-PDF
+`--password` option. JSON output includes per-page Markdown, source/model
+provenance, confidence, timings, warnings, routed pages, and hosted-fallback
+recommendations. Page numbers in `OcrPdfResult` and its per-page provenance
+are 1-indexed, matching the PDF page numbers accepted by `OcrPdfOptions::pages`.
+
 Extract per-page Markdown (one string per page, plus document-wide layout
 metadata):
 

src/bin/pdf2md.rs

@@ -1,6 +1,11 @@
 //! CLI tool for PDF to Markdown conversion
 
 use pdf_inspector::extractor::ItemType;
+#[cfg(all(feature = "ocr", not(target_arch = "wasm32")))]
+use pdf_inspector::vision::{
+    process_pdf_with_ocr, ModelDownloadPolicy, OcrMode, OcrOptions, OcrPdfOptions, OcrPdfResult,
+    PageContentSource, RenderOptions,
+};
 use pdf_inspector::{
     extract_text_with_positions_pages_with_password, process_pdf_with_options, LayoutComplexity,
     PdfOptions, PdfType, ProcessMode, TextItem,
@@ -103,6 +108,134 @@ fn format_items_json(items: &[TextItem]) -> String {
     )
 }
 
+#[cfg(all(feature = "ocr", not(target_arch = "wasm32")))]
+fn optional_json_number(value: Option<f32>) -> String {
+    value
+        .filter(|value| value.is_finite())
+        .map(|value| format!("{value:.4}"))
+        .unwrap_or_else(|| "null".to_string())
+}
+
+#[cfg(all(feature = "ocr", not(target_arch = "wasm32")))]
+fn format_ocr_json(result: &OcrPdfResult) -> String {
+    let routed = result
+        .pages_routed_to_ocr
+        .iter()
+        .map(u32::to_string)
+        .collect::<Vec<_>>()
+        .join(",");
+    let recommended = result
+        .pages_recommended_for_ocr
+        .iter()
+        .map(u32::to_string)
+        .collect::<Vec<_>>()
+        .join(",");
+    let hosted = result
+        .pages_recommending_hosted
+        .iter()
+        .map(u32::to_string)
+        .collect::<Vec<_>>()
+        .join(",");
+    let pages = result
+        .pages
+        .iter()
+        .map(|page| {
+            let provenance = &page.provenance;
+            let source = match provenance.source {
+                PageContentSource::Native => "native",
+                PageContentSource::Ocr => "ocr",
+                PageContentSource::Fused => "fused",
+                _ => "unknown",
+            };
+            let model = provenance
+                .ocr_model
+                .as_ref()
+                .map(|model| {
+                    format!(
+                        r#"{{"name":"{}","revision":"{}"}}"#,
+                        json_escape(&model.name),
+                        json_escape(&model.revision)
+                    )
+                })
+                .unwrap_or_else(|| "null".to_string());
+            let warnings = provenance
+                .warnings
+                .iter()
+                .map(|warning| format!(r#""{}""#, json_escape(warning)))
+                .collect::<Vec<_>>()
+                .join(",");
+            format!(
+                r#"{{"page":{},"source":"{}","markdown":"{}","ocr_model":{},"render_dpi":{},"ocr_confidence":{},"hosted_recommended":{},"timings":{{"render_ms":{},"ocr_ms":{},"layout_ms":{},"assembly_ms":{}}},"warnings":[{}]}}"#,
+                provenance.page,
+                source,
+                json_escape(&page.markdown),
+                model,
+                optional_json_number(provenance.render_dpi),
+                optional_json_number(provenance.ocr_confidence),
+                provenance.hosted_recommended,
+                provenance.timings.render_ms,
+                provenance.timings.ocr_ms,
+                provenance.timings.layout_ms,
+                provenance.timings.assembly_ms,
+                warnings,
+            )
+        })
+        .collect::<Vec<_>>()
+        .join(",");
+    let table_pages = result
+        .pages_with_tables
+        .iter()
+        .map(u32::to_string)
+        .collect::<Vec<_>>()
+        .join(",");
+    let column_pages = result
+        .pages_with_columns
+        .iter()
+        .map(u32::to_string)
+        .collect::<Vec<_>>()
+        .join(",");
+    let ocr_reasons = format_ocr_reasons_by_page(&result.ocr_reasons_by_page);
+    format!(
+        r#"{{"page_count":{},"processing_time_ms":{},"render_time_ms":{},"ocr_time_ms":{},"pages_recommended_for_ocr":[{}],"pages_routed_to_ocr":[{}],"pages_recommending_hosted":[{}],"ocr_reasons_by_page":[{}],"is_complex":{},"pages_with_tables":[{}],"pages_with_columns":[{}],"pages":[{}],"markdown":"{}"}}"#,
+        result.page_count,
+        result.processing_time_ms,
+        result.render_time_ms,
+        result.ocr_time_ms,
+        recommended,
+        routed,
+        hosted,
+        ocr_reasons,
+        result.is_complex,
+        table_pages,
+        column_pages,
+        pages,
+        json_escape(&result.markdown),
+    )
+}
+
+fn argument_value<'a>(args: &'a [String], name: &str) -> Result<Option<&'a str>, String> {
+    args.iter()
+        .position(|argument| argument == name)
+        .map(|index| {
+            args.get(index + 1)
+                .map(String::as_str)
+                .ok_or_else(|| format!("{name} requires a value"))
+        })
+        .transpose()
+}
+
+#[cfg(all(feature = "ocr", not(target_arch = "wasm32")))]
+fn float_argument(args: &[String], name: &str, default: f32) -> Result<f32, String> {
+    argument_value(args, name)?
+        .map(|value| {
+            value
+                .parse::<f32>()
+                .map_err(|_| format!("{name} requires a number, got {value:?}"))
+        })
+        .transpose()
+        .map(|value| value.unwrap_or(default))
+}
+
 fn extract_items_json(
     pdf_path: &str,
     page_filter: Option<&HashSet<u32>>,
@@ -242,6 +375,12 @@ fn main() {
         eprintln!("  --password PW       Password for an encrypted PDF");
         eprintln!("  --detect-only       Only detect PDF type (no extraction)");
         eprintln!("  --analyze           Detect + extract + layout analysis (no markdown)");
+        eprintln!("  --ocr MODE          OCR mode: off, auto, or force (requires feature `ocr`)");
+        eprintln!("  --ocr-dpi N         OCR render resolution (default: 150)");
+        eprintln!("  --ocr-min-confidence N  Drop OCR spans below N (default: 0)");
+        eprintln!("  --ocr-hosted-threshold N  Recommend hosted parsing below N (default: 0.5)");
+        eprintln!("  --ocr-model-dir DIR Use a package-managed local model directory");
+        eprintln!("  --ocr-offline       Never download missing OCR models");
         process::exit(1);
     }
 
@@ -253,6 +392,10 @@ fn main() {
     let page_numbers = args.iter().any(|a| a == "--pages");
     let detect_only = args.iter().any(|a| a == "--detect-only");
     let analyze = args.iter().any(|a| a == "--analyze");
+    let ocr_mode_argument = argument_value(&args, "--ocr").unwrap_or_else(|error| {
+        eprintln!("Error: {error}");
+        process::exit(1);
+    });
 
     // Parse --password value
     let password = args.iter().position(|a| a == "--password").map(|i| {
@@ -283,6 +426,141 @@ fn main() {
             })
         });
 
+    let output_file = args
+        .get(2)
+        .filter(|a| !a.starts_with("--"))
+        .map(|s| s.as_str());
+
+    let has_ocr_only_option = [
+        "--ocr-dpi",
+        "--ocr-min-confidence",
+        "--ocr-hosted-threshold",
+        "--ocr-model-dir",
+        "--ocr-offline",
+    ]
+    .iter()
+    .any(|option| args.iter().any(|argument| argument == option));
+    if ocr_mode_argument.is_none() && has_ocr_only_option {
+        eprintln!("Error: OCR options require --ocr off, --ocr auto, or --ocr force");
+        process::exit(1);
+    }
+
+    if let Some(mode) = ocr_mode_argument {
+        if items_json_output || detect_only || analyze {
+            eprintln!(
+                "Error: --ocr cannot be combined with --items-json, --detect-only, or --analyze"
+            );
+            process::exit(1);
+        }
+
+        #[cfg(not(all(feature = "ocr", not(target_arch = "wasm32"))))]
+        {
+            let _ = mode;
+            eprintln!("Error: this pdf2md build does not include OCR; rebuild with --features ocr");
+            process::exit(1);
+        }
+
+        #[cfg(all(feature = "ocr", not(target_arch = "wasm32")))]
+        {
+            let mode = match mode {
+                "off" => OcrMode::Off,
+                "auto" => OcrMode::Auto,
+                "force" => OcrMode::Force,
+                value => {
+                    eprintln!("Error: invalid --ocr mode {value:?}; expected off, auto, or force");
+                    process::exit(1);
+                }
+            };
+            let dpi = float_argument(&args, "--ocr-dpi", 150.0).unwrap_or_else(|error| {
+                eprintln!("Error: {error}");
+                process::exit(1);
+            });
+            let minimum_confidence = float_argument(&args, "--ocr-min-confidence", 0.0)
+                .unwrap_or_else(|error| {
+                    eprintln!("Error: {error}");
+                    process::exit(1);
+                });
+            let hosted_threshold = float_argument(&args, "--ocr-hosted-threshold", 0.5)
+                .unwrap_or_else(|error| {
+                    eprintln!("Error: {error}");
+                    process::exit(1);
+                });
+            let model_directory =
+                argument_value(&args, "--ocr-model-dir").unwrap_or_else(|error| {
+                    eprintln!("Error: {error}");
+                    process::exit(1);
+                });
+
+            let mut ocr = OcrOptions::new()
+                .mode(mode)
+                .minimum_confidence(minimum_confidence);
+            if let Some(directory) = model_directory {
+                ocr = ocr.model_directory(directory);
+            }
+            if args.iter().any(|argument| argument == "--ocr-offline") {
+                ocr = ocr.model_downloads(ModelDownloadPolicy::Offline);
+            }
+            let mut markdown = pdf_inspector::MarkdownOptions::default();
+            if compact_output {
+                markdown.profile = pdf_inspector::MarkdownProfile::Compact;
+            }
+            markdown.include_page_numbers = page_numbers;
+            let mut pdf_options = OcrPdfOptions::new()
+                .render(RenderOptions::new().dpi(dpi))
+                .ocr(ocr)
+                .markdown(markdown)
+                .hosted_recommendation_confidence(hosted_threshold);
+            if let Some(pages) = page_filter.clone() {
+                pdf_options = pdf_options.pages(pages);
+            }
+            if let Some(password) = password.clone() {
+                pdf_options = pdf_options.password(password);
+            }
+
+            match process_pdf_with_ocr(pdf_path, pdf_options) {
+                Ok(result) => {
+                    if json_output {
+                        println!("{}", format_ocr_json(&result));
+                    } else if raw_output {
+                        print!("{}", result.markdown);
+                    } else {
+                        eprintln!("PDF to Markdown Conversion (OCR)");
+                        eprintln!("======================================");
+                        eprintln!("File: {pdf_path}");
+                        eprintln!("Pages: {}", result.page_count);
+                        eprintln!("Pages routed to OCR: {:?}", result.pages_routed_to_ocr);
+                        if !result.pages_recommending_hosted.is_empty() {
+                            eprintln!(
+                                "Hosted parsing recommended for pages: {:?}",
+                                result.pages_recommending_hosted
+                            );
+                        }
+                        eprintln!("Processing time: {}ms", result.processing_time_ms);
+                        if let Some(output) = output_file {
+                            fs::write(output, &result.markdown)
+                                .expect("Failed to write output file");
+                            eprintln!("Markdown written to: {output}");
+                        } else {
+                            eprintln!();
+                            eprintln!("--- Markdown Output ---");
+                            eprintln!();
+                            print!("{}", result.markdown);
+                        }
+                    }
+                }
+                Err(error) => {
+                    if json_output {
+                        println!(r#"{{"error":"{}"}}"#, json_escape(&error.to_string()));
+                    } else {
+                        eprintln!("Error: {error}");
+                    }
+                    process::exit(1);
+                }
+            }
+            return;
+        }
+    }
+
     if items_json_output {
         match extract_items_json(pdf_path, page_filter.as_ref(), password.as_deref()) {
             Ok(json) => println!("{}", json),
@@ -294,11 +572,6 @@ fn main() {
         return;
     }
 
-    let output_file = args
-        .get(2)
-        .filter(|a| !a.starts_with("--"))
-        .map(|s| s.as_str());
-
     let process_mode = if detect_only {
         ProcessMode::DetectOnly
     } else if analyze {

src/lib.rs

@@ -459,8 +459,35 @@ pub fn extract_pages_markdown_mem(
     buffer: &[u8],
     pages: Option<&[u32]>,
 ) -> Result<PagesExtractionResult, PdfError> {
+    extract_pages_markdown_mem_impl(buffer, pages, None, &MarkdownOptions::default(), false)
+        .map(|(result, _)| result)
+}
+
+#[cfg(all(feature = "ocr", not(target_arch = "wasm32")))]
+pub(crate) fn extract_pages_markdown_mem_for_ocr(
+    buffer: &[u8],
+    pages: Option<&[u32]>,
+    password: Option<&str>,
+    markdown_options: &MarkdownOptions,
+) -> Result<(PagesExtractionResult, u32), PdfError> {
+    extract_pages_markdown_mem_impl(
+        buffer,
+        pages,
+        password,
+        markdown_options,
+        markdown_options.strip_headers_footers,
+    )
+}
+
+fn extract_pages_markdown_mem_impl(
+    buffer: &[u8],
+    pages: Option<&[u32]>,
+    password: Option<&str>,
+    markdown_options: &MarkdownOptions,
+    strip_repeated_headers_footers: bool,
+) -> Result<(PagesExtractionResult, u32), PdfError> {
     validate_pdf_bytes(buffer)?;
-    let (doc, page_count) = load_document_from_mem(buffer)?;
+    let (doc, page_count) = load_document_from_mem_with_password(buffer, password)?;
     let font_cmaps = FontCMaps::from_doc(&doc);
 
     // Extract ALL pages to get accurate, document-wide font stats. A malformed
@@ -503,6 +530,11 @@ pub fn extract_pages_markdown_mem(
 
     // Compute font stats from full document (cross-page consistency).
     let font_stats = markdown::analysis::calculate_font_stats_from_items(&filtered_items);
+    let repeated_header_footer_items = if strip_repeated_headers_footers {
+        repeated_header_footer_item_keys(&all_items, &page_thresholds, &chart_regions, page_count)
+    } else {
+        HashSet::new()
+    };
 
     // When caller doesn't specify pages, return every page in document order.
     let all_pages: Vec<u32>;
@@ -538,7 +570,10 @@ pub fn extract_pages_markdown_mem(
         let (page_items, page_number_removal_mask): (Vec<TextItem>, Vec<bool>) = all_items
             .iter()
             .zip(&page_number_removal_mask)
-            .filter(|(item, _)| item.page == page_1idx)
+            .filter(|(item, _)| {
+                item.page == page_1idx
+                    && !repeated_header_footer_items.contains(&HeaderFooterItemKey::from(*item))
+            })
             .map(|(item, remove)| (item.clone(), *remove))
             .unzip();
 
@@ -575,7 +610,7 @@ pub fn extract_pages_markdown_mem(
             base_font_size: Some(font_stats.most_common_size),
             include_page_numbers: false,
             strip_headers_footers: false,
-            ..MarkdownOptions::default()
+            ..markdown_options.clone()
         };
 
         let md = if has_text_quality_issue {
@@ -634,14 +669,129 @@ pub fn extract_pages_markdown_mem(
         });
     }
 
-    Ok(PagesExtractionResult {
-        pages: results,
-        pages_with_tables: complexity.pages_with_tables,
-        pages_with_columns: complexity.pages_with_columns,
-        pages_needing_ocr,
-        ocr_reasons_by_page: page_ocr_reasons_vec(ocr_reasons_by_page),
-        is_complex: complexity.is_complex,
-    })
+    Ok((
+        PagesExtractionResult {
+            pages: results,
+            pages_with_tables: complexity.pages_with_tables,
+            pages_with_columns: complexity.pages_with_columns,
+            pages_needing_ocr,
+            ocr_reasons_by_page: page_ocr_reasons_vec(ocr_reasons_by_page),
+            is_complex: complexity.is_complex,
+        },
+        page_count,
+    ))
+}
+
+#[derive(Debug, Clone, PartialEq, Eq, Hash)]
+struct HeaderFooterItemKey {
+    page: u32,
+    x: u32,
+    y: u32,
+    text: String,
+}
+
+impl From<&TextItem> for HeaderFooterItemKey {
+    fn from(item: &TextItem) -> Self {
+        Self {
+            page: item.page,
+            x: item.x.to_bits(),
+            y: item.y.to_bits(),
+            text: item.text.clone(),
+        }
+    }
+}
+
+fn repeated_header_footer_item_keys(
+    items: &[TextItem],
+    page_thresholds: &HashMap<u32, f32>,
+    chart_regions: &HashMap<u32, Vec<(f32, f32, f32, f32)>>,
+    page_count: u32,
+) -> HashSet<HeaderFooterItemKey> {
+    let candidates = items
+        .iter()
+        .filter(|item| {
+            matches!(
+                item.item_type,
+                types::ItemType::Text | types::ItemType::FormField
+            )
+        })
+        .cloned()
+        .collect();
+    let lines = extractor::group_prefiltered_items_into_lines_with_thresholds_and_charts(
+        candidates,
+        page_thresholds,
+        &HashSet::new(),
+        chart_regions,
+    );
+    let all_items: HashSet<_> = lines
+        .iter()
+        .flat_map(|line| line.items.iter().map(HeaderFooterItemKey::from))
+        .collect();
+    let kept = markdown::strip_repeated_header_footer_lines(lines, page_count);
+    let kept_items: HashSet<_> = kept
+        .iter()
+        .flat_map(|line| line.items.iter().map(HeaderFooterItemKey::from))
+        .collect();
+    all_items.difference(&kept_items).cloned().collect()
+}
+
+#[cfg(all(test, feature = "ocr", not(target_arch = "wasm32")))]
+mod ocr_header_footer_tests {
+    use super::*;
+
+    fn item(page: u32, text: &str, y: f32) -> TextItem {
+        TextItem {
+            text: text.to_string(),
+            x: 10.0,
+            y,
+            width: 120.0,
+            height: 10.0,
+            font: "Test".to_string(),
+            font_size: 10.0,
+            page,
+            is_bold: false,
+            is_italic: false,
+            is_underline: false,
+            is_strikeout: false,
+            item_type: types::ItemType::Text,
+            mcid: None,
+        }
+    }
+
+    #[test]
+    fn local_pipeline_prefilters_document_wide_repeated_headers() {
+        let mut items = Vec::new();
+        let mut thresholds = HashMap::new();
+        for page in 1..=3 {
+            items.push(item(page, "Repeated report header", 800.0));
+            for line in 0..12 {
+                items.push(item(
+                    page,
+                    &format!("Page {page} paragraph {line} unique content"),
+                    700.0 - line as f32 * 40.0,
+                ));
+            }
+            thresholds.insert(page, 0.1);
+        }
+
+        let removed = repeated_header_footer_item_keys(&items, &thresholds, &HashMap::new(), 3);
+        assert_eq!(removed.len(), 2);
+        for page in 1..=3 {
+            assert_eq!(
+                removed.contains(&HeaderFooterItemKey::from(&item(
+                    page,
+                    "Repeated report header",
+                    800.0,
+                ))),
+                page > 1,
+            );
+            assert!(!removed.contains(&HeaderFooterItemKey::from(&item(
+                page,
+                &format!("Page {page} paragraph 5 unique content"),
+                500.0,
+            ))));
+        }
+    }
 }
 
 /// Path-based wrapper for [`extract_pages_markdown_mem`].

src/markdown/mod.rs

@@ -1144,6 +1144,14 @@ pub fn to_markdown(text: &str, options: MarkdownOptions) -> String {
     output
 }
 
+/// Applies the document-wide repeated header/footer classifier to grouped lines.
+pub(crate) fn strip_repeated_header_footer_lines(
+    lines: Vec<crate::types::TextLine>,
+    page_count: u32,
+) -> Vec<crate::types::TextLine> {
+    preprocess::strip_repeated_lines(lines, page_count)
+}
+
 /// Convert positioned text items to markdown with structure detection
 pub fn to_markdown_from_items(items: Vec<TextItem>, options: MarkdownOptions) -> String {
     to_markdown_from_items_with_rects(items, options, &[])

src/vision/fusion.rs

@@ -62,6 +62,11 @@ impl OcrFusionOptions {
         self.hosted_recommendation_confidence = confidence;
         self
     }
+
+    /// Validates rendering and hosted-fallback thresholds without doing work.
+    pub fn validate(&self) -> Result<(), OcrFusionError> {
+        validate_options(self)
+    }
 }
 
 /// Final Markdown and provenance for one page.

src/vision/mod.rs

@@ -18,6 +18,8 @@ mod fusion;
 mod models;
 #[cfg(all(feature = "ocr-oar", not(target_arch = "wasm32")))]
 mod oar;
+#[cfg(all(feature = "ocr", not(target_arch = "wasm32")))]
+mod pipeline;
 #[cfg(all(feature = "vision", not(target_arch = "wasm32")))]
 mod render;
 #[cfg(all(feature = "vision", not(target_arch = "wasm32")))]
@@ -46,6 +48,10 @@ pub use models::{
 };
 #[cfg(all(feature = "ocr-oar", not(target_arch = "wasm32")))]
 pub use oar::{OarOcrEngine, OarOcrError, ONNX_RUNTIME_LIBRARY_ENV};
+#[cfg(all(feature = "ocr", not(target_arch = "wasm32")))]
+pub use pipeline::{
+    process_pdf_with_ocr, process_pdf_with_ocr_mem, OcrPdfOptions, OcrPdfResult, OcrPipelineError,
+};
 #[cfg(all(feature = "vision", not(target_arch = "wasm32")))]
 pub use render::{
     PagePoint, PageTransform, RenderBufferError, RenderOptions, RenderPixelFormat, RenderedPage,

src/vision/pipeline.rs

@@ -0,0 +1,426 @@
+//! One-call native extraction and OCR pipeline.
+
+use std::collections::BTreeSet;
+use std::path::Path;
+use std::time::Instant;
+
+use thiserror::Error;
+
+use crate::{MarkdownOptions, PageOcrReasons, PdfError};
+
+use super::{
+    fuse_ocr_pages, route_ocr_pages, run_ocr_pages, FusedPageMarkdown, HttpModelDownloadError,
+    HttpModelDownloader, ModelAcquireError, ModelStore, ModelStoreError, OarOcrEngine, OarOcrError,
+    OcrFusionError, OcrFusionOptions, OcrMode, OcrOptions, OcrRoutingError, OcrRun, OcrRunError,
+    PdfiumRenderer, RenderError, RenderOptions, PP_OCR_V6_SMALL,
+};
+
+/// Options for native extraction with optional OCR.
+#[derive(Clone)]
+pub struct OcrPdfOptions {
+    /// Page rasterization settings used when OCR is routed.
+    pub render: RenderOptions,
+    /// OCR routing, model, and recognition settings.
+    pub ocr: OcrOptions,
+    /// Markdown formatting shared by native and OCR assembly.
+    pub markdown: MarkdownOptions,
+    /// Optional 1-indexed page selection. `None` processes the full document.
+    pub page_filter: Option<BTreeSet<u32>>,
+    /// Password for an encrypted PDF.
+    pub password: Option<String>,
+    /// Weak OCR threshold for recommending the hosted pipeline.
+    pub hosted_recommendation_confidence: f32,
+}
+
+impl Default for OcrPdfOptions {
+    fn default() -> Self {
+        Self {
+            render: RenderOptions::default(),
+            ocr: OcrOptions::default(),
+            markdown: MarkdownOptions::default(),
+            page_filter: None,
+            password: None,
+            hosted_recommendation_confidence: 0.5,
+        }
+    }
+}
+
+impl std::fmt::Debug for OcrPdfOptions {
+    fn fmt(&self, formatter: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        formatter
+            .debug_struct("OcrPdfOptions")
+            .field("render", &self.render)
+            .field("ocr", &self.ocr)
+            .field("markdown", &self.markdown)
+            .field("page_filter", &self.page_filter)
+            .field("password", &self.password.as_ref().map(|_| "[REDACTED]"))
+            .field(
+                "hosted_recommendation_confidence",
+                &self.hosted_recommendation_confidence,
+            )
+            .finish()
+    }
+}
+
+impl OcrPdfOptions {
+    /// Creates options with OCR disabled, preserving the native-only path.
+    pub fn new() -> Self {
+        Self::default()
+    }
+
+    /// Replaces page rasterization settings.
+    pub fn render(mut self, render: RenderOptions) -> Self {
+        self.render = render;
+        self
+    }
+
+    /// Replaces OCR routing and recognition settings.
+    pub fn ocr(mut self, ocr: OcrOptions) -> Self {
+        self.ocr = ocr;
+        self
+    }
+
+    /// Sets OCR routing without changing the remaining OCR settings.
+    pub fn mode(mut self, mode: OcrMode) -> Self {
+        self.ocr.mode = mode;
+        self
+    }
+
+    /// Replaces Markdown formatting options.
+    pub fn markdown(mut self, markdown: MarkdownOptions) -> Self {
+        self.markdown = markdown;
+        self
+    }
+
+    /// Restricts processing to 1-indexed pages in ascending order.
+    pub fn pages(mut self, pages: impl IntoIterator<Item = u32>) -> Self {
+        self.page_filter = Some(pages.into_iter().collect());
+        self
+    }
+
+    /// Sets the password used to decrypt the PDF.
+    pub fn password(mut self, password: impl Into<String>) -> Self {
+        self.password = Some(password.into());
+        self
+    }
+
+    /// Sets the weak-OCR threshold for recommending hosted document parsing.
+    pub fn hosted_recommendation_confidence(mut self, confidence: f32) -> Self {
+        self.hosted_recommendation_confidence = confidence;
+        self
+    }
+}
+
+/// Complete native/OCR Markdown output for a PDF request.
+#[derive(Debug, Clone, PartialEq)]
+pub struct OcrPdfResult {
+    /// Final document Markdown in selected-page order.
+    pub markdown: String,
+    /// Final per-page Markdown and provenance, using 1-indexed page numbers.
+    pub pages: Vec<FusedPageMarkdown>,
+    /// Total pages in the PDF, independent of page selection.
+    pub page_count: u32,
+    /// 1-indexed selected pages recommended for OCR by native extraction.
+    pub pages_recommended_for_ocr: Vec<u32>,
+    /// 1-indexed pages actually rendered and recognized.
+    pub pages_routed_to_ocr: Vec<u32>,
+    /// 1-indexed pages whose OCR result recommends hosted document parsing.
+    pub pages_recommending_hosted: Vec<u32>,
+    /// Original machine-readable OCR reasons for selected pages.
+    pub ocr_reasons_by_page: Vec<PageOcrReasons>,
+    /// Selected pages where deterministic table detection found tables.
+    pub pages_with_tables: Vec<u32>,
+    /// Selected pages where deterministic layout found multiple columns.
+    pub pages_with_columns: Vec<u32>,
+    /// Whether deterministic extraction found tables or columns.
+    pub is_complex: bool,
+    /// End-to-end processing time.
+    pub processing_time_ms: u64,
+    /// Batch page-rendering time; zero when no OCR work was routed.
+    pub render_time_ms: u64,
+    /// Batch OCR time; zero when no OCR work was routed.
+    pub ocr_time_ms: u64,
+}
+
+/// Processes a PDF file through native extraction and selective OCR.
+pub fn process_pdf_with_ocr(
+    path: impl AsRef<Path>,
+    options: OcrPdfOptions,
+) -> Result<OcrPdfResult, OcrPipelineError> {
+    let bytes = std::fs::read(path).map_err(PdfError::from)?;
+    process_pdf_with_ocr_mem(&bytes, options)
+}
+
+/// Processes PDF bytes through native extraction and selective OCR.
+///
+/// Native extraction always runs first. `Auto` initializes PDFium, downloads
+/// models, and starts OAR only if the detector selected at least one page.
+/// `Off` therefore has no renderer, model-cache, network, or inference side
+/// effects even though the complete feature is compiled into the application.
+pub fn process_pdf_with_ocr_mem(
+    buffer: &[u8],
+    options: OcrPdfOptions,
+) -> Result<OcrPdfResult, OcrPipelineError> {
+    OcrFusionOptions::new()
+        .render_dpi(options.render.dpi)
+        .hosted_recommendation_confidence(options.hosted_recommendation_confidence)
+        .validate()?;
+    let minimum_confidence = options.ocr.minimum_confidence;
+    if !minimum_confidence.is_finite() || !(0.0..=1.0).contains(&minimum_confidence) {
+        return Err(OcrPipelineError::InvalidMinimumConfidence {
+            value: minimum_confidence,
+        });
+    }
+    if options
+        .page_filter
+        .as_ref()
+        .is_some_and(|pages| pages.contains(&0))
+    {
+        return Err(OcrPipelineError::InvalidSelectedPage { page: 0 });
+    }
+
+    let started = Instant::now();
+    let selected_pages: Option<Vec<u32>> = options
+        .page_filter
+        .as_ref()
+        .map(|pages| pages.iter().copied().collect());
+    let selected_pages_zero_indexed: Option<Vec<u32>> = selected_pages
+        .as_ref()
+        .map(|pages| pages.iter().map(|page| page - 1).collect());
+
+    let mut page_markdown_options = options.markdown.clone();
+    page_markdown_options.include_page_numbers = false;
+    let (native, page_count) = crate::extract_pages_markdown_mem_for_ocr(
+        buffer,
+        selected_pages_zero_indexed.as_deref(),
+        options.password.as_deref(),
+        &page_markdown_options,
+    )?;
+    if let Some(invalid) = selected_pages
+        .as_ref()
+        .and_then(|pages| pages.iter().copied().find(|page| *page > page_count))
+    {
+        return Err(OcrPipelineError::InvalidSelectedPage { page: invalid });
+    }
+
+    let routed = route_ocr_pages(
+        options.ocr.mode,
+        page_count,
+        &native.pages_needing_ocr,
+        selected_pages.as_deref(),
+    )?;
+
+    let ocr_run = if routed.is_empty() {
+        OcrRun {
+            pages: Vec::new(),
+            render_time_ms: 0,
+            ocr_time_ms: 0,
+        }
+    } else {
+        // Resolve the native renderer before any network request so a missing
+        // PDFium installation cannot trigger a model download it cannot use.
+        let renderer = PdfiumRenderer::load()?;
+        let store = ModelStore::from_options(&options.ocr)?;
+        let models = store.resolve_or_download(
+            &PP_OCR_V6_SMALL,
+            options.ocr.model_downloads,
+            &HttpModelDownloader::default(),
+        )?;
+        let engine = OarOcrEngine::from_models(&models)?;
+        run_ocr_pages(
+            &renderer,
+            &engine,
+            buffer,
+            &routed,
+            options.password.as_deref(),
+            &options.render,
+            &options.ocr,
+        )?
+    };
+
+    let fusion_options = OcrFusionOptions::new()
+        .markdown(page_markdown_options)
+        .render_dpi(options.render.dpi)
+        .hosted_recommendation_confidence(options.hosted_recommendation_confidence);
+    let fused = fuse_ocr_pages(&native.pages, &ocr_run, page_count, &fusion_options)?;
+    let pages_recommending_hosted = fused
+        .pages
+        .iter()
+        .filter(|page| page.provenance.hosted_recommended)
+        .map(|page| page.provenance.page)
+        .collect();
+    let markdown = assemble_document_markdown(&fused.pages, options.markdown.include_page_numbers);
+
+    Ok(OcrPdfResult {
+        markdown,
+        pages: fused.pages,
+        page_count,
+        pages_recommended_for_ocr: native.pages_needing_ocr,
+        pages_routed_to_ocr: routed,
+        pages_recommending_hosted,
+        ocr_reasons_by_page: native.ocr_reasons_by_page,
+        pages_with_tables: native.pages_with_tables,
+        pages_with_columns: native.pages_with_columns,
+        is_complex: native.is_complex,
+        processing_time_ms: elapsed_ms(started),
+        render_time_ms: fused.render_time_ms,
+        ocr_time_ms: fused.ocr_time_ms,
+    })
+}
+
+fn assemble_document_markdown(pages: &[FusedPageMarkdown], include_page_numbers: bool) -> String {
+    let mut document = String::new();
+    for (index, page) in pages.iter().enumerate() {
+        if index > 0 {
+            document.push_str("\n\n");
+        }
+        if include_page_numbers {
+            document.push_str(&format!("<!-- Page {} -->\n\n", page.page));
+        }
+        document.push_str(page.markdown.trim());
+    }
+    if !document.is_empty() {
+        document.push('\n');
+    }
+    document
+}
+
+fn elapsed_ms(started: Instant) -> u64 {
+    u64::try_from(started.elapsed().as_millis()).unwrap_or(u64::MAX)
+}
+
+/// Failures from the complete OCR pipeline.
+#[derive(Debug, Error)]
+#[non_exhaustive]
+pub enum OcrPipelineError {
+    /// PDF loading or native extraction failed.
+    #[error(transparent)]
+    Pdf(#[from] PdfError),
+    /// Page routing rejected an invalid request.
+    #[error(transparent)]
+    Routing(#[from] OcrRoutingError),
+    /// The model cache could not be located or initialized.
+    #[error(transparent)]
+    ModelStore(#[from] ModelStoreError),
+    /// A pinned model set could not be resolved or acquired.
+    #[error(transparent)]
+    ModelAcquire(#[from] ModelAcquireError<HttpModelDownloadError>),
+    /// PDFium could not load or rasterize the request.
+    #[error(transparent)]
+    Render(#[from] RenderError),
+    /// The OAR engine could not initialize.
+    #[error(transparent)]
+    Oar(#[from] OarOcrError),
+    /// Selective rendering or OCR execution failed.
+    #[error(transparent)]
+    Run(#[from] OcrRunError),
+    /// OCR/native Markdown fusion failed.
+    #[error(transparent)]
+    Fusion(#[from] OcrFusionError),
+    /// Page zero is invalid because public page selections are 1-indexed.
+    #[error("selected page {page} is invalid; page numbers are 1-indexed")]
+    InvalidSelectedPage {
+        /// Invalid page number.
+        page: u32,
+    },
+    /// OCR span confidence is outside the inclusive 0–1 range.
+    #[error("minimum OCR confidence must be between 0 and 1, got {value}")]
+    InvalidMinimumConfidence {
+        /// Invalid value.
+        value: f32,
+    },
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn off_mode_extracts_native_text_without_runtime_side_effects() {
+        let bytes = std::fs::read("tests/fixtures/thermo-freon12.pdf").unwrap();
+        let result = process_pdf_with_ocr_mem(&bytes, OcrPdfOptions::new()).unwrap();
+
+        assert_eq!(result.page_count, 3);
+        assert_eq!(result.pages.len(), 3);
+        assert!(result.markdown.contains("Thermodynamic Properties"));
+        assert!(result.pages_recommended_for_ocr.is_empty());
+        assert!(result.pages_routed_to_ocr.is_empty());
+        assert!(result.pages_recommending_hosted.is_empty());
+        assert_eq!(result.render_time_ms, 0);
+        assert_eq!(result.ocr_time_ms, 0);
+    }
+
+    #[test]
+    fn auto_mode_does_not_load_pdfium_or_models_for_clean_pdf() {
+        let bytes = std::fs::read("tests/fixtures/thermo-freon12.pdf").unwrap();
+        let result =
+            process_pdf_with_ocr_mem(&bytes, OcrPdfOptions::new().mode(OcrMode::Auto)).unwrap();
+
+        assert!(result.pages_routed_to_ocr.is_empty());
+        assert!(result.markdown.contains("Freon 12"));
+    }
+
+    #[test]
+    fn selection_and_page_markers_use_public_one_indexed_pages() {
+        let bytes = std::fs::read("tests/fixtures/thermo-freon12.pdf").unwrap();
+        let mut markdown = MarkdownOptions::default();
+        markdown.include_page_numbers = true;
+        let result =
+            process_pdf_with_ocr_mem(&bytes, OcrPdfOptions::new().pages([2]).markdown(markdown))
+                .unwrap();
+
+        assert_eq!(result.pages.len(), 1);
+        assert_eq!(result.pages[0].page, 2);
+        assert_eq!(result.pages[0].page, result.pages[0].provenance.page);
+        assert!(result.markdown.starts_with("<!-- Page 2 -->"));
+    }
+
+    #[test]
+    fn off_mode_marks_unprocessed_scan_for_hosted_fallback() {
+        let bytes = std::fs::read("tests/fixtures/scan_with_native_header_text.pdf").unwrap();
+        let result = process_pdf_with_ocr_mem(&bytes, OcrPdfOptions::new()).unwrap();
+
+        assert!(result.pages_routed_to_ocr.is_empty());
+        assert_eq!(result.pages_recommending_hosted, vec![1]);
+    }
+
+    #[test]
+    fn password_is_redacted_and_used_for_native_extraction() {
+        let options = OcrPdfOptions::new().password("secret123");
+        assert!(!format!("{options:?}").contains("secret123"));
+
+        let bytes = std::fs::read("tests/fixtures/encrypted-secret123.pdf").unwrap();
+        let result = process_pdf_with_ocr_mem(&bytes, options).unwrap();
+        assert!(result.markdown.contains("Procurement"));
+    }
+
+    #[test]
+    fn rejects_out_of_range_selection_even_with_ocr_off() {
+        let bytes = std::fs::read("tests/fixtures/thermo-freon12.pdf").unwrap();
+        let error = process_pdf_with_ocr_mem(&bytes, OcrPdfOptions::new().pages([4])).unwrap_err();
+        assert!(matches!(
+            error,
+            OcrPipelineError::InvalidSelectedPage { page: 4 }
+        ));
+    }
+
+    #[test]
+    fn invalid_expensive_options_fail_before_pdf_or_runtime_access() {
+        let mut invalid_dpi = OcrPdfOptions::new();
+        invalid_dpi.render.dpi = f32::NAN;
+        assert!(matches!(
+            process_pdf_with_ocr_mem(b"not a PDF", invalid_dpi),
+            Err(OcrPipelineError::Fusion(
+                OcrFusionError::InvalidRenderDpi { .. }
+            ))
+        ));
+
+        let invalid_hosted = OcrPdfOptions::new().hosted_recommendation_confidence(1.1);
+        assert!(matches!(
+            process_pdf_with_ocr_mem(b"not a PDF", invalid_hosted),
+            Err(OcrPipelineError::Fusion(
+                OcrFusionError::InvalidHostedConfidence { .. }
+            ))
+        ));
+    }
+}

tests/ocr_tests.rs

@@ -1,5 +1,9 @@
 #![cfg(all(feature = "ocr-oar", not(target_arch = "wasm32")))]
 
+#[cfg(feature = "ocr")]
+use pdf_inspector::vision::{
+    process_pdf_with_ocr_mem, ModelDownloadPolicy, OcrPdfOptions, PageContentSource,
+};
 use pdf_inspector::vision::{
     ModelStore, OarOcrEngine, OcrEngine, OcrMode, OcrOptions, PageTransform, RenderPixelFormat,
     RenderedPage, PP_OCR_V6_SMALL,
@@ -100,6 +104,34 @@ fn recognizes_a_pdfium_rendered_fixture_with_verified_models() {
     assert_usable_result(&results);
 }
 
+#[cfg(all(feature = "ocr", feature = "render-pdfium"))]
+#[test]
+fn complete_ocr_pipeline_routes_and_assembles_a_scanned_fixture() {
+    let Some(model_directory) = std::env::var_os(MODEL_DIRECTORY_ENV) else {
+        eprintln!("skipping OCR runtime test because {MODEL_DIRECTORY_ENV} is not set");
+        return;
+    };
+    let Some(_renderer) = load_renderer() else {
+        return;
+    };
+
+    let bytes = std::fs::read("tests/fixtures/scan_with_native_header_text.pdf").unwrap();
+    let ocr = OcrOptions::new()
+        .mode(OcrMode::Auto)
+        .minimum_confidence(0.3)
+        .model_directory(model_directory)
+        .model_downloads(ModelDownloadPolicy::Offline);
+    let result = process_pdf_with_ocr_mem(&bytes, OcrPdfOptions::new().ocr(ocr)).unwrap();
+
+    assert_eq!(result.pages_routed_to_ocr, vec![1]);
+    assert!(!result.markdown.trim().is_empty());
+    assert_eq!(result.pages[0].provenance.source, PageContentSource::Ocr);
+    assert_eq!(
+        result.pages[0].provenance.ocr_model.as_ref().unwrap().name,
+        PP_OCR_V6_SMALL.id
+    );
+}
+
 fn recognize(
     model_directory: &std::ffi::OsStr,
     pages: &[RenderedPage],