hackerncoder/stuff
1
0
Fork 0
Code Issues Pull requests Actions Packages Projects Releases Wiki Activity

cook: Better comp + cli output. Cleanup.

Browse source
This commit is contained in:
HackerNCoder 2024-02-23 02:40:53 +01:00
parent 9850e93d89
commit d5db6efde3
1 changed files with 22 additions and 24 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

46
cook.py
View file

@ -1,10 +1,8 @@
from zipfile import ZipFile from zipfile import ZipFile
from pathlib import Path from pathlib import Path
import os, sys, time, re, shutil, argparse import os, sys, re, shutil, argparse
parser = argparse.ArgumentParser("epub cooking") parser = argparse.ArgumentParser("epub cooking")
parser.add_argument("--cc", metavar="CHAPTERS_CLASS", help="The class used in chapters. (default: hlink)", type=str)
parser.add_argument("--fc", metavar="FOOTNOTES_CLASS", help="The class used in footnotes. (default: hanging1)", type=str)
#parser.add_argument("--test", help="Test a link or footnote against the regex. (NotImplemented)", type=bool) #parser.add_argument("--test", help="Test a link or footnote against the regex. (NotImplemented)", type=bool)
parser.add_argument("file", help="The file to be worked on.", type=str) parser.add_argument("file", help="The file to be worked on.", type=str)
args = parser.parse_args() args = parser.parse_args()
@ -12,27 +10,22 @@ args = parser.parse_args()
file_name = args.file file_name = args.file
files_to_work_on = [] files_to_work_on = []
files_to_zip = [] files_to_zip = []
lastItemLength = 1
if args.cc:
chapter_class = args.cc
else:
chapter_class = "hlink" #VHS: Change hlink, this is the class found in the chapters
if args.fc:
footnotes_class = args.fc
else:
footnotes_class = "hanging1" # VHS: Change hanging1, this is the class found in the footnotes
def progressbar(it, prefix="", size=60, out=sys.stdout): # Python3.6+ def progressbar(it, prefix="", size=60, out=sys.stdout): # Python3.6+
count = len(it) count = len(it)
start = time.time() def show(j, item):
def show(j): global lastItemLength
x = int(size*j/count) x = int(size*j/count)
spacesToPrint = lastItemLength - len(item)
print(f"{prefix}[{u'█'*x}{('.'*(size-x))}] {j}/{count}", end='\r', file=out, flush=True)
print(f"{prefix}[{u'█'*x}{('.'*(size-x))}] {j}/{count} (Currently working on: {item}){' '*spacesToPrint}", end='\r', file=out, flush=True)
lastItemLength = len(item)
for i, item in enumerate(it): for i, item in enumerate(it):
yield item yield item
show(i+1) show(i+1, item)
print(f"{prefix}[{u'█'*size}] {count}/{count} {' '*lastItemLength}", end='\r', file=out, flush=True)
print("\n", flush=True, file=out) print("\n", flush=True, file=out)
class NoStdStreams(object): class NoStdStreams(object):
@ -54,7 +47,7 @@ class NoStdStreams(object):
with ZipFile(file_name, 'r') as zip: with ZipFile(file_name, 'r') as zip:
for filename in zip.namelist(): for filename in zip.namelist():
if re.search('.x?html?', filename): if re.search('.*?(?!titlepage).*?\.x?html?$', filename):
zip.extract(filename) zip.extract(filename)
files_to_work_on.append(filename) files_to_work_on.append(filename)
@ -63,24 +56,28 @@ Path(f"work/{files_to_work_on[2].split('/')[0]}").mkdir(parents=True, exist_ok=T
print(f"Cooking on {file_name}, with {len(files_to_work_on)} files in it") print(f"Cooking on {file_name}, with {len(files_to_work_on)} files in it")
for file in files_to_work_on: #progressbar(files_to_work_on, "", 40): for file in progressbar(files_to_work_on, "", 40):
with open(file, 'r') as epub_file: with open(file, 'r') as epub_file:
text = epub_file.read() text = epub_file.read()
test = re.findall('id="toc"|epub:type="toc"', text) test = re.findall('id="toc"|epub:type=".*?toc.*?"|epub:type=".*?frontmatter.*?"|epub:type=".*?backmatter.*?"|epub:type=".*?appendix.*?"', text)
if test: if test:
print(f"Skipping {file}, it seems to not be a chapter{' '*42}")
continue continue
matches = re.findall(f'<a (?:(?:class="{chapter_class}")|(?:href="(.*?)#(.*?)")|(?:.*?))+>', text) matches = re.findall(f'<a[\w\d\s="-]*?href="(.*?)#(.*?)"[\w\d\s="-]*?>', text)
if matches: if matches:
for match in matches: for match in matches:
if match[0] != '': if match[0] != '' and not re.search("toc\.x?html?", match[0]):
for dd in files_to_work_on: for dd in files_to_work_on:
if re.search(f".*?{match[0]}.*?", dd): if re.search(f".*?{match[0]}.*?", dd):
with open(dd, 'r') as source: with open(dd, 'r') as source:
source_match = re.search(f"<p class=\"{footnotes_class}\".*?id=\"{match[1]}\".*?</p>", source.read()) test = re.findall('id="toc"|epub:type=".*?toc.*?"|epub:type=".*?frontmatter.*?"|epub:type=".*?backmatter.*?"|epub:type=".*?appendix.*?"', text)
if test:
continue
source_match = re.search(f"<p.*?id=\"{match[1]}\".*?</p>", source.read())
if source_match: if source_match:
source_match_fixed = re.sub('<p(?:(.*?)?(?:id=".*?")?)><a.*?<\/a>[\.\s ]*(.*?)<\/p>', rf'<p\1 id={match[1]}>\2</p>', source_match.group()) source_match_fixed = re.sub('<p(?:(.*?)?(?:id=".*?")?)><a.*?<\/a>[\.\s ]*(.*?)<\/p>', rf'<p\1 id="{match[1]}">\2</p>', source_match.group())
source_match_fixed = re.sub('<p (.*?)</p>', r'<p epub:type="footnote" \1</p>', source_match_fixed) source_match_fixed = re.sub('<p (.*?)</p>', r'<p epub:type="footnote" \1</p>', source_match_fixed)
fixed_text = re.sub(f"<a (?:(?:class=\"{chapter_class}\")|(?:href=\".*?#{match[1]}\")|(?:.*?))+>", f"<a epub:type=\"noteref\" class=\"{chapter_class}\" href=\"#{match[1]}\">", text) fixed_text = re.sub(f'<a (?:(?:href=".*?#.*?")|(class=".*?")|(?:.*?))+>', fr'<a epub:type="noteref" \1 href="#{match[1]}">', text)
text = re.sub(f"\n\s*</body>", f"\n{source_match_fixed}\n</body>", fixed_text) text = re.sub(f"\n\s*</body>", f"\n{source_match_fixed}\n</body>", fixed_text)
with open(f"work/{file}", 'w') as output: with open(f"work/{file}", 'w') as output:
output.write(text) output.write(text)
@ -94,3 +91,4 @@ with ZipFile("output.epub", 'a') as zip:
zip.write(f"work/{file}", file) zip.write(f"work/{file}", file)
shutil.rmtree("work") shutil.rmtree("work")
shutil.rmtree(f"{files_to_work_on[2].split('/')[0]}")