fix(pdf-text): add error management

Inist-CNRS · Sep 23, 2024 · 2f72145 · 2f72145
1 parent 3d8ed2c
commit 2f72145
Show file tree

Hide file tree

Showing 2 changed files with 14 additions and 22 deletions.
diff --git a/services/pdf-text/v1/pdf-raw.py b/services/pdf-text/v1/pdf-raw.py
@@ -20,17 +20,7 @@
 
 def convert_pdf_to_xml(input_path):
     result = subprocess.run(['pdftohtml','-xml', '-stdout','-hidden','-i','-q','-f',p, input_path], capture_output=True, text=True)
-
-    # Check if conversion was successful
-    if result.returncode == 0:
-        # Get the XML content in a variable
-        xml_content = result.stdout
-        return xml_content
-    else:
-        # print error message if needed
-        sys.stderr.write(f"Conversion of PDF {input_path} to XML has failed.")
-        sys.stderr.write("\n")
-        return None
+    return result.stdout
 
 
 def remove_xml_tags(xml_string):
@@ -212,6 +202,12 @@ def get_alphabetic_numeric_ratio(chaine):
     except OSError :
         #print("Erreur lors de la suppression du fichier PDF:", e)
         line0['value']="Erreur lors de la suppression du fichier PDF"
+
+    except Exception :
+        line0['value']="Erreur lors de la conversion du PDF en texte"
+
+    if line0['value']=="":
+        line0['value']="Erreur lors de la conversion du PDF en texte"
 
     sys.stdout.write(json.dumps(line0))
     sys.stdout.write('\n')
diff --git a/services/pdf-text/v1/pdf2txt.py b/services/pdf-text/v1/pdf2txt.py
@@ -24,17 +24,7 @@
 
 def convert_pdf_to_xml(input_path):
     result = subprocess.run(['pdftohtml','-xml', '-stdout','-hidden','-i','-q','-f',p, input_path], capture_output=True, text=True)
-
-    # Check if conversion was successful
-    if result.returncode == 0:
-        # Get the XML content in a variable
-        xml_content = result.stdout
-        return xml_content
-    else:
-        # print error message if needed
-        sys.stderr.write(f"Conversion of PDF {input_path} to XML has failed.")
-        sys.stderr.write("\n")
-        return None
+    return result.stdout
 
 
 def remove_xml_tags(xml_string):
@@ -226,6 +216,12 @@ def get_alphabetic_numeric_ratio(chaine):
     except OSError :
         #print("Erreur lors de la suppression du fichier PDF:", e)
         line0['value']="Erreur lors de la suppression du fichier PDF"
+
+    except Exception :
+        line0['value']="Erreur lors de la conversion du PDF en texte"
 
+    if line0['value']=="":
+        line0['value']="Erreur lors de la conversion du PDF en texte"
+
     sys.stdout.write(json.dumps(line0))
     sys.stdout.write('\n')