glyphlist bug (due to my misunderstanding of spec.)

git-svn-id: https://pdfminerr.googlecode.com/svn/trunk/pdfminer@237 1aa58f4a-7d42-0410-adbc-911cccaed67c

pdfminer/cmapdb.py

@@ -163,7 +163,7 @@ class FileUnicodeMap(UnicodeMap):
         assert isinstance(cid, int)
         if isinstance(code, PSLiteral):
             # Interpret as an Adobe glyph name.
-            self.cid2unichr[cid] = unichr(name2unicode(code.name))
+            self.cid2unichr[cid] = name2unicode(code.name)
         elif isinstance(code, str):
             # Interpret as UTF-16BE.
             self.cid2unichr[cid] = unicode(code, 'UTF-16BE', 'ignore')

pdfminer/encodingdb.py

@@ -2,7 +2,7 @@
 
 import re
 from psparser import PSLiteral
-from glyphlist import charname2unicode
+from glyphlist import glyphname2unicode
 from latin_enc import ENCODING
 
 
@@ -11,11 +11,11 @@ from latin_enc import ENCODING
 STRIP_NAME = re.compile(r'[0-9]+')
 def name2unicode(name):
     """Converts Adobe glyph names to Unicode numbers."""
-    if name in charname2unicode:
+    if name in glyphname2unicode:
-        return charname2unicode[name]
+        return glyphname2unicode[name]
     m = STRIP_NAME.search(name)
     if not m: raise KeyError(name)
-    return int(m.group(0))
+    return unichr(int(m.group(0)))
 
 
 ##  EncodingDB
@@ -27,7 +27,7 @@ class EncodingDB(object):
     win2unicode = {}
     pdf2unicode = {}
     for (name,std,mac,win,pdf) in ENCODING:
-        c = unichr(name2unicode(name))
+        c = name2unicode(name)
         if std: std2unicode[std] = c
         if mac: mac2unicode[mac] = c
         if win: win2unicode[win] = c
@@ -51,7 +51,7 @@ class EncodingDB(object):
                     cid = x
                 elif isinstance(x, PSLiteral):
                     try:
-                        cid2unicode[cid] = unichr(name2unicode(x.name))
+                        cid2unicode[cid] = name2unicode(x.name)
                     except KeyError:
                         pass
                     cid += 1

pdfminer/layout.py

@@ -212,6 +212,7 @@ class LTChar(LTItem, LTText):
         self.adv = font.char_width(cid) * fontsize * scaling
         try:
             text = font.to_unichr(cid)
+            assert isinstance(text, unicode), text
         except PDFUnicodeNotDefined:
             text = '?'
         (a,b,c,d,e,f) = self.matrix

pdfminer/pdfdevice.py

@@ -159,7 +159,7 @@ class TagExtractor(PDFDevice):
 
     def begin_tag(self, tag, props=None):
         s = ''
-        if props:
+        if isinstance(props, dict):
             s = ''.join( ' %s="%s"' % (enc(k), enc(str(v))) for (k,v)
                          in sorted(props.iteritems()) )
         self.outfp.write('<%s%s>' % (enc(tag.name), s))

tools/conv_afm.py

@@ -1,8 +1,6 @@
 #!/usr/bin/env python
 import sys
 import fileinput
-stdout = sys.stdout
-stderr = sys.stderr
 
 def main(argv):
     fonts = {}

tools/conv_glyphlist.py

@@ -0,0 +1,24 @@
+#!/usr/bin/env python
+import sys
+import fileinput
+
+def main(argv):
+    state = 0
+    for line in fileinput.input():
+        line = line.strip()
+        if not line or line.startswith('#'):
+            if state == 1:
+                state = 2
+                print '}'
+                print
+            print line
+            continue
+        if state == 0:
+            print
+            print 'glyphname2unicode = {'
+            state = 1
+        (name,x) = line.split(';')
+        codes = x.split(' ')
+        print ' %r: u\'%s\',' % (name, ''.join( '\\u%s' % code for code in codes ))
+
+if __name__ == '__main__': sys.exit(main(sys.argv))