MindWorkAI/AI-Studio
MindWorkAI/AI-Studio
1
0
Fork 0
mirror of https://github.com/MindWorkAI/AI-Studio.git synced 2026-08-11 18:32:12 +00:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

Improved the log output while reading documents

Browse Source
This commit is contained in:
Thorsten Sommer 2026-08-10 20:34:02 +02:00
parent d11de0b5be
commit 8a2414720b
Signed by untrusted user who does not match committer: tsommer
GPG Key ID: 371BBA77A02C0108
1 changed files with 6 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
runtime/src/file_data.rs
View File

@ -1028,10 +1028,13 @@ async fn stream_document(file_path: &str, extract_images: bool, stream_id: &str)
// Page iteration performs synchronous ZIP/XML work and image compression, // Page iteration performs synchronous ZIP/XML work and image compression,
// so the complete producer must stay outside Tokio's asynchronous workers. // so the complete producer must stay outside Tokio's asynchronous workers.
let worker = tokio::task::spawn_blocking(move || { let worker = tokio::task::spawn_blocking(move || {
//
// Failures travel through the error channel, which logs them with the file path and the
// classified code once they arrive. Logging them here as well would only duplicate that.
//
let document = match DocumentContainer::open(&path, parser_config) { let document = match DocumentContainer::open(&path, parser_config) {
Ok(document) => document, Ok(document) => document,
Err(e) => { Err(e) => {
error!("The document '{path:?}' could not be opened: {e}");
let _ = tx.blocking_send(Err(ExtractionError::new( let _ = tx.blocking_send(Err(ExtractionError::new(
ExtractionErrorCode::FileNotReadable, ExtractionErrorCode::FileNotReadable,
format!("The document could not be read: {e}"), format!("The document could not be read: {e}"),
@ -1043,7 +1046,6 @@ async fn stream_document(file_path: &str, extract_images: bool, stream_id: &str)
let pages = match document.iter_pages() { let pages = match document.iter_pages() {
Ok(pages) => pages, Ok(pages) => pages,
Err(e) => { Err(e) => {
error!("The pages of the document '{path:?}' could not be read: {e}");
let _ = tx.blocking_send(Err(ExtractionError::new( let _ = tx.blocking_send(Err(ExtractionError::new(
ExtractionErrorCode::FileNotReadable, ExtractionErrorCode::FileNotReadable,
format!("The pages of the document could not be read: {e}"), format!("The pages of the document could not be read: {e}"),
@ -1066,7 +1068,6 @@ async fn stream_document(file_path: &str, extract_images: bool, stream_id: &str)
let page = match page_result { let page = match page_result {
Ok(page) => page, Ok(page) => page,
Err(e) => { Err(e) => {
error!("A page of the document '{path:?}' could not be read: {e}");
let _ = tx.blocking_send(Err(ExtractionError::new( let _ = tx.blocking_send(Err(ExtractionError::new(
ExtractionErrorCode::Internal, ExtractionErrorCode::Internal,
format!("A page of the document could not be read: {e}"), format!("A page of the document could not be read: {e}"),
@ -1077,7 +1078,6 @@ async fn stream_document(file_path: &str, extract_images: bool, stream_id: &str)
let mut content = match page.to_markdown() { let mut content = match page.to_markdown() {
Ok(content) => content, Ok(content) => content,
Err(e) => { Err(e) => {
error!("Page {page_number} of the document '{path:?}' could not be converted: {e}", page_number = page.page_number);
let _ = tx.blocking_send(Err(ExtractionError::new( let _ = tx.blocking_send(Err(ExtractionError::new(
ExtractionErrorCode::Internal, ExtractionErrorCode::Internal,
format!("Page {page_number} of the document could not be converted: {e}", page_number = page.page_number), format!("Page {page_number} of the document could not be converted: {e}", page_number = page.page_number),
@ -1119,14 +1119,14 @@ async fn stream_document(file_path: &str, extract_images: bool, stream_id: &str)
} }
} }
debug!("Extracted {number_of_characters} character(s) from {number_of_pages} page(s) of '{path:?}'."); debug!("Extracted {number_of_characters} character(s) from {number_of_pages} page(s) of '{path}'.", path = path.display());
// //
// Without this marker, a document without any text and a broken extraction both arrive as // Without this marker, a document without any text and a broken extraction both arrive as
// an empty document, and the AI would answer as if the file had no content at all. // an empty document, and the AI would answer as if the file had no content at all.
// //
if number_of_characters == 0 { if number_of_characters == 0 {
warn!("No text could be extracted from '{path:?}': {number_of_pages} page(s)."); warn!("No text could be extracted from '{path}': {number_of_pages} page(s).", path = path.display());
let _ = tx.blocking_send(Ok(Chunk::from_error(&ExtractionError::new( let _ = tx.blocking_send(Ok(Chunk::from_error(&ExtractionError::new(
ExtractionErrorCode::NoTextExtracted, ExtractionErrorCode::NoTextExtracted,