Merge pull request #7867 from lrineau/Scripts-improve_add_toc_to_github_wiki_page.py-GF

Improve add_toc_to_github_wiki_page.py

Scripts/developer_scripts/add_toc_to_github_wiki_page.py

@@ -1,20 +1,21 @@
-from sys import argv
-from sys import exit
 import codecs
 import re
 import argparse
+import sys
+from urllib.parse import quote
 
 parser = argparse.ArgumentParser()
-parser.add_argument("filename",
-                    help="the Mardown file to process")
-parser.add_argument("--codebase",
+parser.add_argument("filename", help="the Markdown file to process")
+parser.add_argument(
+    "--codebase",
     help="for a Markdown file of Codebase instead of Github",
-                    action="store_true")
-parser.add_argument("--h1",
-                    help="support level one sections (h1)",
-                    action="store_true")
+    action="store_true",
+)
+parser.add_argument("--h1", help="support level one sections (h1)", action="store_true")
+parser.add_argument("--max-level", help="maximum level of sections", type=int, default = 5)
 args = parser.parse_args()
 
+
 # a probably incomplete version to generate an anchor from a section name
 def get_anchor(s):
     s = s.replace("`", "")
@@ -38,28 +39,31 @@ def get_anchor(s):
     s = s.lstrip(" ")
     s = s.rstrip("\n")
     s = s.rstrip(" ")
-  s = re.sub(r'\s+','-',s)
+    s = re.sub(r"\s+", "-", s)
     if not args.codebase:
         s = s.lower()
     if args.codebase:
         s = s.replace("'", "-and-39-")
-  return "#"+s
+    return "#" + quote(s)
+
 
 # indices the nesting level (first level allowed is ##)
 def get_level(s):
-  m = re.search('^(#+)\s', s)
+    m = re.search(r"^(#+)\s", s)
     if m:
         return len(m.group(1))
     else:
         return 0
 
+
 def get_name(s):
-  m = re.search('^#+\s+(.*)\s*$', s)
+    m = re.search(r"^#+\s+(.*)\s*$", s)
     if m:
         return m.group(1)
     else:
         return "ERROR: Section name extraction"
 
+
 # generate the entry for one section
 def get_toc_entry(s):
     name = get_name(s)
@@ -73,23 +77,25 @@ def get_toc_entry(s):
         return "ERROR: h1 sections are not allowed"
 
     res = "* [" + name + "](" + anchor + ")"
-  for i in range(0,level):
+    for _ in range(0, level):
         res = "  " + res
     return res
 
-#now the main
-input = args.filename
 
-f = codecs.open(input, 'r', encoding='utf-8')
+# now the main
+def main():
+    filename = args.filename
+
+    f = codecs.open(filename, "r", encoding="utf-8")
 
     if not f:
         print("Cannot open " + input + "\n")
-  exit()
+        sys.exit()
 
     # look for <!--TOC--> the begin of the file
     line = f.readline()
     if line.find("<!--TOC-->") == -1:
-  exit()
+        sys.exit()
 
     # skip current TOC
     line = f.readline()
@@ -97,13 +103,13 @@ while line and line.find("<!--TOC-->")==-1:
         line = f.readline()
 
     if not line:
-  exit()
+        sys.exit()
 
     buffer = ""
-TOC="<!--TOC-->\n\n# Table of Contents\n"
+    toc = "<!--TOC-->\n\n# Table of Contents\n"
 
     verbatim_mode = False  # to ignore verbatim mode while looking for sections
-TOC_empty=True
+    toc_empty = True
     for line in f.readlines():
         buffer += line
         if verbatim_mode:
@@ -113,13 +119,16 @@ for line in f.readlines():
             if line[:3] == "```":
                 verbatim_mode = True
             else:
-      if line[0]=="#":
-        TOC+=(get_toc_entry(line)+"\n")
-        TOC_empty=False
-TOC+="\n<!--TOC-->\n"
+                if line[0] == "#" and get_level(line) <= args.max_level:
+                    toc += get_toc_entry(line) + "\n"
+                    toc_empty = False
+    toc += "\n<!--TOC-->\n"
 
-if not TOC_empty:
+    if not toc_empty:
         f.close()
-  f = codecs.open(input, 'w', encoding='utf-8')
-  f.write(TOC)
+        f = codecs.open(filename, "w", encoding="utf-8")
+        f.write(toc)
         f.write(buffer)
+
+if __name__ == "__main__":
+    main()