Update markdoku for python3 compat

diff --git a/markdoku.py b/markdoku.py
index 3c87132ee61a130ffcd39b69cc109da2e3c3ba47..d4e307012e963ef4588b7c82f6acc906a582084c 100644 (file)
--- a/markdoku.py
+++ b/markdoku.py
@@ -94,7 +94,7 @@ except ImportError:
 import optparse
 from random import random, randint
 import codecs
-from urllib import quote
+from urllib.parse import quote
 
 
 
@@ -123,12 +123,12 @@ DEFAULT_TAB_WIDTH = 4
 try:
     import uuid
 except ImportError:
-    SECRET_SALT = str(randint(0, 1000000))
+    SECRET_SALT = str(randint(0, 1000000)).encode('utf-8')
 else:
-    SECRET_SALT = str(uuid.uuid4())
+    SECRET_SALT = str(uuid.uuid4()).encode('utf-8')
 def _hash_ascii(s):
     #return md5(s).hexdigest()   # Markdown.pl effectively does this.
-    return 'md5-' + md5(SECRET_SALT + s).hexdigest()
+    return 'md5-' + md5(SECRET_SALT + s.encode("utf-8")).hexdigest()
 def _hash_text(s):
     return 'md5-' + md5(SECRET_SALT + s.encode("utf-8")).hexdigest()
 
@@ -253,9 +253,9 @@ class Markdown(object):
         # articles):
         self.reset()
 
-        if not isinstance(text, unicode):
+        if not isinstance(text, str):
             #TODO: perhaps shouldn't presume UTF-8 for string input?
-            text = unicode(text, 'utf-8')
+            text = text.decode('utf-8')
 
         if self.use_file_vars:
             # Look for emacs-style file variable hints.
@@ -578,11 +578,11 @@ class Markdown(object):
                 # Delimiters for next comment block.
                 try:
                     start_idx = text.index("<!--", start)
-                except ValueError, ex:
+                except ValueError as ex:
                     break
                 try:
                     end_idx = text.index("-->", start_idx) + 3
-                except ValueError, ex:
+                except ValueError as ex:
                     break
 
                 # Start position for next comment block search.
@@ -1810,7 +1810,7 @@ class MarkdownWithExtras(Markdown):
 
 #---- internal support functions
 
-class UnicodeWithAttrs(unicode):
+class UnicodeWithAttrs(str):
     """A subclass of unicode used for the return value of conversion to
     possibly attach some attributes. E.g. the "toc_html" attribute when
     the "toc" extra is used.
@@ -1921,8 +1921,7 @@ def _dedentlines(lines, tabsize=8, skip_first_line=False):
     """
     DEBUG = False
     if DEBUG: 
-        print "dedent: dedent(..., tabsize=%d, skip_first_line=%r)"\
-              % (tabsize, skip_first_line)
+        print(f"dedent: dedent(..., tabsize={tabsize}, skip_first_line={skip_first_line})")
     indents = []
     margin = None
     for i, line in enumerate(lines):
@@ -1939,12 +1938,12 @@ def _dedentlines(lines, tabsize=8, skip_first_line=False):
                 break
         else:
             continue # skip all-whitespace lines
-        if DEBUG: print "dedent: indent=%d: %r" % (indent, line)
+        if DEBUG: print(f"dedent: indent={indent}: {line}")
         if margin is None:
             margin = indent
         else:
             margin = min(margin, indent)
-    if DEBUG: print "dedent: margin=%r" % margin
+    if DEBUG: print(f"dedent: margin={margin}")
 
     if margin is not None and margin > 0:
         for i, line in enumerate(lines):
@@ -1956,7 +1955,7 @@ def _dedentlines(lines, tabsize=8, skip_first_line=False):
                 elif ch == '\t':
                     removed += tabsize - (removed % tabsize)
                 elif ch in '\r\n':
-                    if DEBUG: print "dedent: %r: EOL -> strip up to EOL" % line
+                    if DEBUG: print("dedent: {line}: EOL -> strip up to EOL")
                     lines[i] = lines[i][j:]
                     break
                 else:
@@ -1964,8 +1963,7 @@ def _dedentlines(lines, tabsize=8, skip_first_line=False):
                                      "line %r while removing %d-space margin"
                                      % (ch, line, margin))
                 if DEBUG:
-                    print "dedent: %r: %r -> removed %d/%d"\
-                          % (line, ch, removed, margin)
+                    print(f"dedent: {line}: {ch} -> removed {removed}/{margin}")
                 if removed == margin:
                     lines[i] = lines[i][j+1:]
                     break
@@ -2185,13 +2183,13 @@ def main(argv=None):
                        "Markdown.pl")
     for path in paths:
         if opts.compare:
-            print "==== Markdown.pl ===="
+            print("==== Markdown.pl ====")
             perl_cmd = 'perl %s "%s"' % (markdown_pl, path)
             o = os.popen(perl_cmd)
             perl_html = o.read()
             o.close()
             sys.stdout.write(perl_html)
-            print "==== markdown2.py ===="
+            print("==== markdown2.py ====")
         html = markdown_path(path, encoding=opts.encoding,
                              html4tags=opts.html4tags,
                              safe_mode=opts.safe_mode,
@@ -2212,7 +2210,8 @@ def main(argv=None):
             else:
                 norm_html = html
                 norm_perl_html = perl_html
-            print "==== match? %r ====" % (norm_perl_html == norm_html)
+            did_match = (norm_perl_html == norm_html)
+            print(f"==== match? {did_match} ====")
 
 
 if __name__ == "__main__":