Improve add_toc_to_github_wiki_page.py

- reformat using `black`
- add an option `--max-level`
- quote anchors (for accentuated character)
- fix linter errors

Scripts/developer_scripts/add_toc_to_github_wiki_page.py

@@ -1,125 +1,130 @@
-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",
+parser.add_argument("filename", help="the Mardown file to process")
-                    help="the Mardown file to process")
+parser.add_argument(
-parser.add_argument("--codebase",
+    "--codebase",
-                    help="for a Markdown file of Codebase instead of Github",
+    help="for a Markdown file of Codebase instead of Github",
-                    action="store_true")
+    action="store_true",
-parser.add_argument("--h1",
+)
-                    help="support level one sections (h1)",
+parser.add_argument("--h1", help="support level one sections (h1)", action="store_true")
-                    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("`","")
+    s = s.replace("`", "")
-  s = s.replace("(","")
+    s = s.replace("(", "")
-  s = s.replace(")","")
+    s = s.replace(")", "")
-  s = s.replace(".","")
+    s = s.replace(".", "")
-  s = s.replace("#","")
+    s = s.replace("#", "")
-  s = s.replace(":","")
+    s = s.replace(":", "")
-  s = s.replace(",","")
+    s = s.replace(",", "")
-  s = s.replace(";","")
+    s = s.replace(";", "")
-  if args.codebase:
+    if args.codebase:
-    s = s.replace("/","-")
+        s = s.replace("/", "-")
-  else:
+    else:
-    s = s.replace("/","")
+        s = s.replace("/", "")
-  s = s.replace("<","")
+    s = s.replace("<", "")
-  s = s.replace(">","")
+    s = s.replace(">", "")
-  s = s.replace("+","")
+    s = s.replace("+", "")
-  s = s.replace("=","")
+    s = s.replace("=", "")
-  s = s.replace("?","")
+    s = s.replace("?", "")
-  s = s.replace("@","")
+    s = s.replace("@", "")
-  s = s.lstrip(" ")
+    s = s.lstrip(" ")
-  s = s.rstrip("\n")
+    s = s.rstrip("\n")
-  s = s.rstrip(" ")
+    s = s.rstrip(" ")
-  s = re.sub(r'\s+','-',s)
+    s = re.sub(r"\s+", "-", s)
-  if not args.codebase:
+    if not args.codebase:
-    s = s.lower()
+        s = s.lower()
-  if args.codebase:
+    if args.codebase:
-    s = s.replace("'","-and-39-")
+        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:
+    if m:
-    return len(m.group(1))
+        return len(m.group(1))
-  else:
+    else:
-    return 0
+        return 0
+
 
 def get_name(s):
-  m = re.search('^#+\s+(.*)\s*$', s)
+    m = re.search(r"^#+\s+(.*)\s*$", s)
-  if m:
+    if m:
-    return m.group(1)
+        return m.group(1)
-  else:
+    else:
-    return "ERROR: Section name extraction"
+        return "ERROR: Section name extraction"
 
-#generate the entry for one section
+
+# generate the entry for one section
 def get_toc_entry(s):
-  name = get_name(s)
+    name = get_name(s)
-  if args.h1:
+    if args.h1:
-    level = get_level(s)-1
+        level = get_level(s) - 1
-  else:
+    else:
-    level = get_level(s)-2
+        level = get_level(s) - 2
-  anchor = get_anchor(s)
+    anchor = get_anchor(s)
 
-  if level<0:
+    if level < 0:
-    return "ERROR: h1 sections are not allowed"
+        return "ERROR: h1 sections are not allowed"
 
-  res="* ["+name+"]("+anchor+")"
+    res = "* [" + name + "](" + anchor + ")"
-  for i in range(0,level):
+    for _ in range(0, level):
-    res="  "+res
+        res = "  " + res
-  return res
+    return res
 
-#now the main
-input = args.filename
 
-f = codecs.open(input, 'r', encoding='utf-8')
+# now the main
+filename = args.filename
+
+f = codecs.open(filename, "r", encoding="utf-8")
 
 if not f:
-  print("Cannot open "+input+"\n")
+    print("Cannot open " + input + "\n")
-  exit()
+    sys.exit()
 
-#look for <!--TOC--> the begin of the file
+# look for <!--TOC--> the begin of the file
-line=f.readline()
+line = f.readline()
-if line.find("<!--TOC-->")==-1:
+if line.find("<!--TOC-->") == -1:
-  exit()
+    sys.exit()
 
-#skip current TOC
+# skip current TOC
-line=f.readline()
+line = f.readline()
-while line and line.find("<!--TOC-->")==-1:
+while line and line.find("<!--TOC-->") == -1:
-  line=f.readline()
+    line = f.readline()
 
 if not line:
-  exit()
+    sys.exit()
 
-buffer=""
+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
+verbatim_mode = False  # to ignore verbatim mode while looking for sections
-TOC_empty=True
+TOC_empty = True
 for line in f.readlines():
-  buffer+=line
+    buffer += line
-  if verbatim_mode:
+    if verbatim_mode:
-    if line[:3]=="```":
+        if line[:3] == "```":
-      verbatim_mode=False
+            verbatim_mode = False
-  else:
-    if line[:3]=="```":
-      verbatim_mode=True
     else:
-      if line[0]=="#":
+        if line[:3] == "```":
-        TOC+=(get_toc_entry(line)+"\n")
+            verbatim_mode = True
-        TOC_empty=False
+        else:
-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:
-  f.close()
+    f.close()
-  f = codecs.open(input, 'w', encoding='utf-8')
+    f = codecs.open(filename, "w", encoding="utf-8")
-  f.write(TOC)
+    f.write(TOC)
-  f.write(buffer)
+    f.write(buffer)