Merge pull request #76 from speedplane/master

Fix Unicode Bug + Add GitIgnore + Add Debug Flags

.gitignore

@@ -0,0 +1,54 @@
+# Intermediate documents
+*.xps
+
+# Password and Key Files
+*.pem
+*.p12
+
+# Compiled source #
+###################
+*.pyc
+*.com
+*.class
+*.dll
+*.exe
+*.o
+*.so
+
+# Mecurial Files?
+*.i
+*.d
+*.mo
+*.hg/
+
+# Python data files #
+*.shelf
+*.shelve
+
+# Don't track these files, they are output from scripts
+
+# Subversion files
+*.svn-base
+all-wcprops
+entries
+
+# Logs and databases #
+######################
+bulkloader-log-*
+*.log
+*.sql
+*.sql3
+*.sql3-journal
+*.sqlite
+
+# OS generated files #
+######################
+.DS_Store?
+ehthumbs.db
+Icon?
+Thumbs.db
+
+# tmp files #
+#############
+~$*.doc
+~WRL*.tmp

pdfminer/pdfdocument.py

@@ -65,6 +65,8 @@ LITERAL_CATALOG = LIT('Catalog')
 ##
 class PDFBaseXRef(object):
 
+    debug = False
+    
     def get_trailer(self):
         raise NotImplementedError
 
@@ -122,7 +124,7 @@ class PDFXRef(PDFBaseXRef):
                 if use != b'n':
                     continue
                 self.offsets[objid] = (None, long(pos), int(genno))
-        logging.info('xref objects: %r' % self.offsets)
+        if self.debug: logging.info('xref objects: %r' % self.offsets)
         self.load_trailer(parser)
         return
 
@@ -173,7 +175,7 @@ class PDFXRefFallback(PDFXRef):
             if line.startswith(b'trailer'):
                 parser.seek(pos)
                 self.load_trailer(parser)
-                logging.info('trailer: %r' % self.get_trailer())
+                if self.debug: logging.info('trailer: %r' % self.get_trailer())
                 break
             m = self.PDFOBJ_CUE.match(line)
             if not m:
@@ -212,6 +214,8 @@ class PDFXRefFallback(PDFXRef):
 ##
 class PDFXRefStream(PDFBaseXRef):
 
+    debug = False
+    
     def __init__(self):
         self.data = None
         self.entlen = None
@@ -238,6 +242,7 @@ class PDFXRefStream(PDFBaseXRef):
         self.data = stream.get_data()
         self.entlen = self.fl1+self.fl2+self.fl3
         self.trailer = stream.attrs
+        if self.debug:
             logging.info('xref stream: objid=%s, fields=%d,%d,%d' %
                      (', '.join(map(repr, self.ranges)),
                       self.fl1, self.fl2, self.fl3))
@@ -761,6 +766,7 @@ class PDFDocument(object):
                 prev = line
         else:
             raise PDFNoValidXRef('Unexpected EOF')
+        if self.debug:
             logging.info('xref found: pos=%r' % prev)
         return long(prev)
 
@@ -773,6 +779,7 @@ class PDFDocument(object):
             (pos, token) = parser.nexttoken()
         except PSEOF:
             raise PDFNoValidXRef('Unexpected EOF')
+        if self.debug:
             logging.info('read_xref_from: start=%d, token=%r' % (start, token))
         if isinstance(token, int):
             # XRefStream: PDF-1.5
@@ -787,6 +794,7 @@ class PDFDocument(object):
             xref.load(parser)
         xrefs.append(xref)
         trailer = xref.get_trailer()
+        if self.debug:
             logging.info('trailer: %r' % trailer)
         if 'XRefStm' in trailer:
             pos = int_value(trailer['XRefStm'])

pdfminer/pdfinterp.py

@@ -139,6 +139,8 @@ class PDFResourceManager(object):
     allocated multiple times.
     """
 
+    debug = False
+    
     def __init__(self, caching=True):
         self.caching = caching
         self._cached_fonts = {}
@@ -167,6 +169,7 @@ class PDFResourceManager(object):
         if objid and objid in self._cached_fonts:
             font = self._cached_fonts[objid]
         else:
+            if self.debug:
                 logging.info('get_font: create: objid=%r, spec=%r' % (objid, spec))
             if STRICT:
                 if spec['Type'] is not LITERAL_FONT:
@@ -799,7 +802,7 @@ class PDFPageInterpreter(object):
             if STRICT:
                 raise PDFInterpreterError('Undefined xobject id: %r' % xobjid)
             return
-        logging.info('Processing xobj: %r' % xobj)
+        if self.debug: logging.info('Processing xobj: %r' % xobj)
         subtype = xobj.get('Subtype')
         if subtype is LITERAL_FORM and 'BBox' in xobj:
             interpreter = self.dup()
@@ -822,7 +825,7 @@ class PDFPageInterpreter(object):
         return
 
     def process_page(self, page):
-        logging.info('Processing page: %r' % page)
+        if self.debug: logging.info('Processing page: %r' % page)
         (x0, y0, x1, y1) = page.mediabox
         if page.rotate == 90:
             ctm = (0, -1, 1, 0, -y0, x1)
@@ -841,6 +844,7 @@ class PDFPageInterpreter(object):
     #   Render the content streams.
     #   This method may be called recursively.
     def render_contents(self, resources, streams, ctm=MATRIX_IDENTITY):
+        if self.debug:
             logging.info('render_contents: resources=%r, streams=%r, ctm=%r' %
                      (resources, streams, ctm))
         self.init_resources(resources)

pdfminer/pdfpage.py

@@ -39,6 +39,8 @@ class PDFPage(object):
       beads: a chain that represents natural reading order.
     """
 
+    debug = False
+
     def __init__(self, doc, pageid, attrs):
         """Initialize a page object.
 
@@ -86,12 +88,12 @@ class PDFPage(object):
                 if k in klass.INHERITABLE_ATTRS and k not in tree:
                     tree[k] = v
             if tree.get('Type') is LITERAL_PAGES and 'Kids' in tree:
-                logging.info('Pages: Kids=%r' % tree['Kids'])
+                if klass.debug: logging.info('Pages: Kids=%r' % tree['Kids'])
                 for c in list_value(tree['Kids']):
                     for x in search(c, tree):
                         yield x
             elif tree.get('Type') is LITERAL_PAGE:
-                logging.info('Page: %r' % tree)
+                if klass.debug: logging.info('Page: %r' % tree)
                 yield (objid, tree)
         pages = False
         if 'Pages' in document.catalog:

pdfminer/psparser.py

@@ -343,7 +343,15 @@ class PSBaseParser(object):
             self.hex = b''
             self._parse1 = self._parse_literal_hex
             return j+1
-        self._add_token(LIT(unicode(self._curtoken)))
+        
+        try:
+            # Try to interpret the token as a utf-8 string
+            utoken = self._curtoken.decode('utf-8')
+        except UnicodeDecodeError:
+            # We failed, there is possibly a corrupt PDF here.
+            if STRICT: raise
+            utoken = ""
+        self._add_token(LIT(utoken))
         self._parse1 = self._parse_main
         return j