fix #193

[nhentai.git] / nhentai / utils.py

diff --git a/nhentai/utils.py b/nhentai/utils.py
index fb7355909fa07d32e750074c2aa34b2d05fd1c7b..099f6a12042912900743a14e20bd1dc3e077766c 100644 (file)
--- a/nhentai/utils.py
+++ b/nhentai/utils.py
@@ -1,10 +1,8 @@
 # coding: utf-8
-from __future__ import unicode_literals, print_function
 
 import sys
 import re
 import os
-import string
 import zipfile
 import shutil
 import requests
@@ -64,7 +62,7 @@ def readfile(path):
         return file.read()
 
 
-def generate_html(output_dir='.', doujinshi_obj=None):
+def generate_html(output_dir='.', doujinshi_obj=None, template='default'):
     image_html = ''
 
     if doujinshi_obj is not None:
@@ -81,9 +79,9 @@ def generate_html(output_dir='.', doujinshi_obj=None):
 
         image_html += '<img src="{0}" class="image-item"/>\n'\
             .format(image)
-    html = readfile('viewer/index.html')
-    css = readfile('viewer/styles.css')
-    js = readfile('viewer/scripts.js')
+    html = readfile('viewer/{}/index.html'.format(template))
+    css = readfile('viewer/{}/styles.css'.format(template))
+    js = readfile('viewer/{}/scripts.js'.format(template))
 
     if doujinshi_obj is not None:
         serialize_json(doujinshi_obj, doujinshi_dir)
@@ -226,22 +224,31 @@ def generate_pdf(output_dir='.', doujinshi_obj=None, rm_origin_dir=False):
     logger.log(15, 'PDF file has been written to \'{0}\''.format(doujinshi_dir))
 
 
-def format_filename(s):
-    """Take a string and return a valid filename constructed from the string.
-Uses a whitelist approach: any characters not present in valid_chars are
-removed. Also spaces are replaced with underscores.
+def unicode_truncate(s, length, encoding='utf-8'):
+    """https://stackoverflow.com/questions/1809531/truncating-unicode-so-it-fits-a-maximum-size-when-encoded-for-wire-transfer
+    """
+    encoded = s.encode(encoding)[:length]
+    return encoded.decode(encoding, 'ignore')
 
-Note: this method may produce invalid filenames such as ``, `.` or `..`
-When I use this method I prepend a date string like '2009_01_15_19_46_32_'
-and append a file extension like '.txt', so I avoid the potential of using
-an invalid filename.
 
-"""
+def format_filename(s):
+    """
+    It used to be a whitelist approach allowed only alphabet and a part of symbols.
+    but most doujinshi's names include Japanese 2-byte characters and these was rejected.
+    so it is using blacklist approach now.
+    if filename include forbidden characters (\'/:,;*?"<>|) ,it replace space character(' '). 
+    """
     # maybe you can use `--format` to select a suitable filename
-    valid_chars = "-_.()[] %s%s" % (string.ascii_letters, string.digits)
-    filename = ''.join(c for c in s if c in valid_chars)
+    ban_chars = '\\\'/:,;*?"<>|\t'
+    filename = s.translate(str.maketrans(ban_chars, ' '*len(ban_chars))).strip()
+    filename = ' '.join(filename.split())
+    print(repr(filename))
+
+    while filename.endswith('.'):
+        filename = filename[:-1]
+
     if len(filename) > 100:
-        filename = filename[:100] + '...]'
+        filename = filename[:100] + u'…'
 
     # Remove [] from filename
     filename = filename.replace('[]', '').strip()