#!/usr/bin/env python3
#
# Copyright (C) 2023 Jonathan A. Poritz
# 
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
# 
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
#
import argparse
import re
import sys
import warnings
if not sys.warnoptions:
    warnings.simplefilter("ignore")
#
# setting up arguments
#
parser = argparse.ArgumentParser(description='Prints layers of headings from an html file such as the "tidy_book.html" produced by OOprep')
parser.add_argument("inputfile", help="File containing html from which to extract outline information.", type=argparse.FileType('r'))
parser.add_argument('-c', '--chapter_nos', help='chapters have numbers, which are used in building the outline numbering', action='store_true')
parser.add_argument('-n', '--numbering', help='print also chapter/section/sub... numbering as it should be', action='store_true')
parser.add_argument('-d', '--dividers', help='print horizontal dividers between blocks at different levels', action='store_true')
parser.add_argument('-t', '--tags', help='print header tags as in the html file', action='store_true')
args = parser.parse_args()
#
# initializing counts of found objects, helpers for output
#
line_no = 0
chap_no = 0
sec_no = 0
ssec_no = 0
sssec_no = 0
ssssec_no = 0
nesting_warnings = 0
tag_warnings = 0
last_level = 0
if args.numbering:
  spaces = 3
else:
  spaces = 2
def warn(s):
  print(f'WARNING: on line {line_no}, with content\n{l}\n{s}')
#
# looping through input file, keeping track of lines which start and end with
#  <h{1-5]> and </h[1-5]>, also checks for improper levels of heading levels
#
for line in args.inputfile:
  line_no += 1
  l = line.strip()
  if l[:4]=="<h1>":
    if l[-5:]!="</h1>":
      warn("expecting entire line bracketed in <h1>..</h1>")
      if args.tags:
        l = l[4:]
    elif not args.tags:
      l = l[4:-5]
    if last_level != 1 and args.dividers:
      print("-"*80)
    last_level = 1
    if args.chapter_nos:
      num = l.split()[1]
      if num[-1] == ":":
        num = num[:-1]
      chap_no = int(num)
    else:
      chap_no += 1
    sec_no = 0
    ssec_no = 0
    sssec_no = 0
    ssssec_no = 0
    if args.numbering:
      print(f'{chap_no:2} {l}')
    else:
      print(l)
    continue
  if l[:4]=="<h2>":
    if l[-5:]!="</h2>":
      warn("expecting entire line bracketed in <h2>..</h2>")
      if args.tags:
        l = l[4:]
    elif not args.tags:
      l = l[4:-5]
    if last_level != 2 and args.dividers:
      print(" "*spaces + "-"*(77-spaces))
    last_level = 2
    if chap_no == 0:
      nesting_warnings += 1
      warn("Section without enclosing chapter")
    sec_no += 1
    ssec_no = 0
    sssec_no = 0
    ssssec_no = 0
    if args.numbering:
      print(f'{chap_no:2}.{sec_no:2} {l}')
    else:
      print("  "+l)
    continue
  if l[:4]=="<h3>":
    if l[-5:]!="</h3>":
      warn("expecting entire line bracketed in <h3>..</h3>")
      if args.tags:
        l = l[4:]
    elif not args.tags:
      l = l[4:-5]
    if last_level != 3 and args.dividers:
      print(" "*spaces*2 + "-"*(77-spaces*2))
    last_level = 3
    if sec_no == 0:
      nesting_warnings += 1
      if chap_no == 0:
        warn("Subsection without enclosing chapter or section")
      else:
        warn("Subsection without enclosing section")
    ssec_no += 1
    sssec_no = 0
    ssssec_no = 0
    if args.numbering:
      print(f'{chap_no:2}.{sec_no:2}.{ssec_no:2} {l}')
    else:
      print("    "+l)
    continue
  if l[:4]=="<h4>":
    if l[-5:]!="</h4>":
      warn("expecting entire line bracketed in <h4>..</h4>")
      if args.tags:
        l = l[4:]
    elif not args.tags:
      l = l[4:-5]
    if last_level != 4 and args.dividers:
      print(" "*spaces*3 + "-"*(77-spaces*3))
    last_level = 4
    if ssec_no ==0:
      nesting_warnings += 1
      if sec_no == 0:
        if chap_no == 0:
          warn("Subsubsection without enclosing chapter, section, or subsection")
        else:
          warn("Subsubsection without enclosing section or subsection")
      else:
        warn("Subsubsection without enclosing subsection")
    sssec_no += 1
    ssssec_no = 0
    if args.numbering:
      print(f'{chap_no:2}.{sec_no:2}.{ssec_no:2}.{sssec_no:2} {l}')
    else:
      print("      "+l)
    continue
  if l[:4]=="<h5>":
    if l[-5:]!="</h5>":
      warn("expecting entire line bracketed in <h5>..</h5>")
      if args.tags:
        l = l[4:]
    elif not args.tags:
      l = l[4:-5]
    if last_level != 5 and args.dividers:
      print(" "*spaces*4 + "-"*(77-spaces*4))
    last_level = 5
    if sssec_no == 0:
      nesting_warnings += 1
      if ssec_no == 0:
        if sec_no == 0:
          if chap_no == 0:
            warn("Subsubsubsection without enclosing chapter, section, subsection, or subsubsection")
          else:
            warn("Subsubsubsection without enclosing section, subsection, or subsubsection")
        else:
          warn("Subsubsubsection without enclosing subsection or subsubsection")
      else:
        warn("Subsubsubsection without enclosing subsubsection")
    ssssec_no += 1
    if args.numbering:
      print(f'{chap_no:2}.{sec_no:2}.{ssec_no:2}.{sssec_no:2}.{ssssec_no:2} {l}')
    else:
      print("       "+l)
if nesting_warnings >1:
  print(f"Note: there were {nesting_warnings} improperly nested section warnings")
if nesting_warnings == 1:
  print(f"Note: there was an improperly nested section warning")