625 support identity cmap

pdfminer/cmapdb.py

@@ -122,6 +122,10 @@ def dump(self, out: TextIO = sys.stdout,
 
 class IdentityCMap(CMapBase):
 
+    def get_unichr(self, cid):
+        log.debug('get_unichr: %r, %r', self, cid)
+        return chr(cid)
+
     def decode(self, code: bytes) -> Tuple[int, ...]:
         n = len(code)//2
         if n:

pdfminer/pdffont.py

@@ -763,9 +763,17 @@ def __init__(
                                BytesIO(self.fontfile.get_data()))
         self.unicode_map: Optional[UnicodeMap] = None
         if 'ToUnicode' in spec:
-            strm = stream_value(spec['ToUnicode'])
-            self.unicode_map = FileUnicodeMap()
-            CMapParser(self.unicode_map, BytesIO(strm.get_data())).run()
+            if isinstance(spec['ToUnicode'], PDFStream):
+                strm = stream_value(spec['ToUnicode'])
+                self.unicode_map = FileUnicodeMap()
+                CMapParser(self.unicode_map, BytesIO(strm.get_data())).run()
+            else:
+                cmap_name = literal_name(spec['ToUnicode'])
+                encoding = literal_name(spec['Encoding'])
+                if 'Identity' in cid_ordering \
+                        or 'Identity' in cmap_name \
+                        or 'Identity' in encoding:
+                    self.unicode_map = self.cmap
         elif self.cidcoding in ('Adobe-Identity', 'Adobe-UCS'):
             if ttf:
                 try:

tests/test_highlevel_extracttext.py

@@ -33,6 +33,7 @@ def run_with_file(sample_path):
     "simple4.pdf": "Text1\nText2\nText3\n\n\f",
     "contrib/issue_566_test_1.pdf": "ISSUE Date：2019-4-25 Buyer：黎荣",
     "contrib/issue_566_test_2.pdf": "甲方：中国饮料有限公司（盖章）",
+    "contrib/issue-625-identity-cmap.pdf": "Termin płatności: 2021-05-03",
 }
 
 
@@ -92,6 +93,12 @@ def test_issue_566_cid_range(self):
         s = run_with_file(test_file)
         self.assertEqual(s.strip(), test_strings[test_file])
 
+    def test_issue_625_identity_cmap(self):
+        test_file = "contrib/issue-625-identity-cmap.pdf"
+        lines = run_with_file(test_file).splitlines()
+
+        self.assertEqual(lines[6], test_strings[test_file])
+
 
 class TestExtractPages(unittest.TestCase):
     def _get_test_file_path(self):