CodeSource
/
Readur
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

fix(ocr): use proper failure reasons to avoid constraint violations in failed_documents table

This commit is contained in:
perf3ct 2025-07-21 20:43:37 +00:00
parent 7ee9a4c6a6
commit 65f42c2cd7
1 changed files with 17 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
src/ocr/queue.rs
View File

@ -428,10 +428,13 @@ impl OcrQueueService {
let error_msg = "OCR update failed validation (document may have been modified)";
warn!("{} for document {}", error_msg, item.document_id);
// Use classification function to determine proper failure reason
let (failure_reason, _should_suppress) = Self::classify_ocr_error(error_msg);
// Create failed document record using helper function
let _ = self.create_failed_document_from_ocr_error(
item.document_id,
"processing",
failure_reason,
error_msg,
item.attempts,
).await;
@ -443,10 +446,13 @@ impl OcrQueueService {
let error_msg = format!("Transaction-safe OCR update failed: {}", e);
error!("{}", error_msg);
// Use classification function to determine proper failure reason
let (failure_reason, _should_suppress) = Self::classify_ocr_error(&error_msg);
// Create failed document record using helper function
let _ = self.create_failed_document_from_ocr_error(
item.document_id,
"processing",
failure_reason,
&error_msg,
item.attempts,
).await;
@ -461,10 +467,13 @@ impl OcrQueueService {
warn!("⚠️ No searchable content extracted for '{}' | Job: {} | Document: {} | 0 words",
filename, item.id, item.document_id);
// Use classification function to determine proper failure reason
let (failure_reason, _should_suppress) = Self::classify_ocr_error(&error_msg);
// Create failed document record using helper function
let _ = self.create_failed_document_from_ocr_error(
item.document_id,
"no_extractable_text",
failure_reason,
&error_msg,
item.attempts,
).await;
@ -1196,8 +1205,12 @@ impl OcrQueueService {
("unsupported_format", false)
} else if error_str.contains("too large") || error_str.contains("file size") {
("file_too_large", false)
} else if error_str.contains("No extractable text") || error_str.contains("0 words") {
("low_ocr_confidence", false) // No extractable text treated as low confidence OCR
} else if error_str.contains("validation") || error_str.contains("document may have been modified") {
("other", false) // Document validation failures use "other"
} else {
("other", false)
("other", false) // Fallback for any unrecognized errors
}
}
}