witten/novel-stats
1
0
Fork 1
Code Issues 1 Pull Requests Releases Activity

Commented my changes + swapped to tempfile library

Browse Source
This commit is contained in:
Dmytro Yeroshkin 2021-10-22 14:28:13 +02:00
parent d79e3f5b80
commit e3a47d7425
1 changed files with 18 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
novel_stats/novel_stats.py
View File

@ -3,13 +3,12 @@
import collections
import sys
import os
CHAPTER_MARKER = '## '
STATUS_MARKER = '[status]: # '
ACT_MARKER = '[act]: # '
COMMENT_MARKER = '[//]: # '
COMMENT_MARKER = '[//]: # ' # Strandard markdown comment marker, supported by pandoc and calibre's ebook-convert
def count_words(line):
@ -27,13 +26,17 @@ def count_words(line):
def main():
arguments = sys.argv[1:]
filename = arguments[0]
tmpfilename = None
mdfile = None
if '-pp' in arguments:
import MarkdownPP
tmpfilename = f'.tmp-{os.getpid}.md'
MarkdownPP.MarkdownPP(input=open(filename), output=open(tmpfilename,'w'), modules=list(MarkdownPP.modules))
filename = tmpfilename
# -pp flag to allow Markdown Preprocessing primarily to allow multi-file novel formatting
# this is implemented using a temporary file created using python's buit-in tempfile library
import MarkdownPP, tempfile
mdfile = tempfile.TemporaryFile(mode='w+')
MarkdownPP.MarkdownPP(input=open(filename), output=mdfile, modules=list(MarkdownPP.modules))
mdfile.seek(0)
else:
mdfile = open(filename)
chapter_heading = None
act_heading = None
@ -44,7 +47,7 @@ def main():
status_by_chapter = {}
current_status = None
for line in open(filename).readlines():
for line in mdfile.readlines():
if line.startswith(CHAPTER_MARKER):
word_count_by_act[act_heading] += word_count_by_chapter[chapter_heading]
total_word_count += word_count_by_chapter[chapter_heading]
@ -55,7 +58,7 @@ def main():
status_by_chapter[chapter_heading] = collections.defaultdict(int)
current_status = None
elif line.startswith(STATUS_MARKER):
elif line.startswith(STATUS_MARKER): # Modified to allow multiple statuses in a single chapter, can swap back and forth.
if current_status == None:
current_status = line[len(STATUS_MARKER):].strip('()\n')
status_by_chapter[chapter_heading][current_status] = count_words(chapter_heading)
@ -65,7 +68,7 @@ def main():
elif line.startswith(ACT_MARKER):
act_heading = line[len(ACT_MARKER):].strip('()\n')
word_count_by_act[act_heading] = count_words(act_heading)
elif line.startswith(COMMENT_MARKER):
elif line.startswith(COMMENT_MARKER): # don't count the words in a comment
pass
else:
line_word_count = count_words(line)
@ -79,8 +82,7 @@ def main():
word_count_by_act[act_heading] += word_count_by_chapter[chapter_heading]
total_word_count += word_count_by_chapter[chapter_heading]
if '-c' in arguments or '--chapter' in arguments:
# Print out word counts.
if '-c' in arguments or '--chapter' in arguments: # -c or --chapter to give a chapter-by-chapter word count summary
for chapter_heading, chapter_word_count in word_count_by_chapter.items():
if chapter_heading is None:
continue
@ -99,7 +101,7 @@ def main():
print()
if '-a' in arguments or '--act' in arguments:
if '-a' in arguments or '--act' in arguments: # -a or --act to give an act-by-act word count summary
for act_heading, act_word_count in word_count_by_act.items():
if act_heading is None:
continue
@ -109,12 +111,11 @@ def main():
print()
for status, status_word_count in word_count_by_status.items():
print('{}: {:,} words (~{}%)'.format(status, status_word_count, status_word_count * 100 // total_word_count))
print(f'{status}: {status_word_count:,} words (~{status_word_count * 100 // total_word_count}%)')
print('total: {:,} words'.format(total_word_count))
print(f'total: {total_word_count:,} words')
if tmpfilename:
os.remove(tmpfilename)
mdfile.close()
if __name__ == '__main__':