Changeset 220 for pkpgcounter/trunk/pdlanalyzer/pdf.py

Timestamp:

07/02/05 15:41:30 (19 years ago)

Author:

jerome

Message:

Big improvements on readability + maintainability

Files:

• pkpgcounter/trunk/pdlanalyzer/pdf.py (modified) (2 diffs)

pkpgcounter/trunk/pdlanalyzer/pdf.py

@@ -27 +27 @@
 from pdlanalyzer import pdlparser
 
-class PDFParser(pdlparser.PDLParser) :
+class Parser(pdlparser.PDLParser) :
     """A parser for PDF documents."""
+    def isValid(self) :    
+        """Returns 1 if data is PDF, else 0."""
+        if self.firstblock.startswith("%PDF-") or \
+           self.firstblock.startswith("\033%-12345X%PDF-") or \
+           ((self.firstblock[:128].find("\033%-12345X") != -1) and (self.firstblock.upper().find("LANGUAGE=PDF") != -1)) or \
+           (self.firstblock.find("%PDF-") != -1) :
+            if self.debug :  
+                sys.stderr.write("DEBUG: Input file is in the PDF format.\n")
+            return 1
+        else :    
+            return 0
+        
     def getJobSize(self) :    
         """Counts pages in a PDF document."""
@@ -56 +68 @@
             mustclose = 1
         try :
-            parser = PDFParser(infile, debug=1)
+            parser = Parser(infile, debug=1)
             totalsize += parser.getJobSize()
         except pdlparser.PDLParserError, msg :