From c497dc1097e708c724ce9ce7223dc37b13d6f94c Mon Sep 17 00:00:00 2001
From: Kovid Goyal <kovid@kovidgoyal.net>
Date: Wed, 1 Jan 2014 11:29:03 +0530
Subject: [PATCH] Edit book: Add a check for too large HTML files when running
 the check book tool. Fixes #1264680 [[Feature Request]: Edit Book 300/100 kb
 warning on HTML](https://bugs.launchpad.net/calibre/+bug/1264680)

---
 src/calibre/ebooks/oeb/polish/check/main.py   |  3 ++-
 .../ebooks/oeb/polish/check/parsing.py        | 20 +++++++++++++++++--
 2 files changed, 20 insertions(+), 3 deletions(-)

diff --git a/src/calibre/ebooks/oeb/polish/check/main.py b/src/calibre/ebooks/oeb/polish/check/main.py
index 146d847171..9e61a7ea5e 100644
--- a/src/calibre/ebooks/oeb/polish/check/main.py
+++ b/src/calibre/ebooks/oeb/polish/check/main.py
@@ -12,7 +12,7 @@ from calibre.ebooks.oeb.base import OEB_DOCS, OEB_STYLES
 from calibre.ebooks.oeb.polish.container import guess_type
 from calibre.ebooks.oeb.polish.cover import is_raster_image
 from calibre.ebooks.oeb.polish.check.base import run_checkers
-from calibre.ebooks.oeb.polish.check.parsing import check_xml_parsing, check_css_parsing, fix_style_tag
+from calibre.ebooks.oeb.polish.check.parsing import check_xml_parsing, check_css_parsing, fix_style_tag, check_html_size
 from calibre.ebooks.oeb.polish.check.images import check_raster_images
 from calibre.ebooks.oeb.polish.check.links import check_links
 from calibre.ebooks.oeb.polish.check.fonts import check_fonts
@@ -37,6 +37,7 @@ def run_checks(container):
             items = raster_images
         if items is not None:
             items.append((name, mt, container.open(name, 'rb').read()))
+    errors.extend(run_checkers(check_html_size, html_items))
     errors.extend(run_checkers(check_xml_parsing, xml_items))
     errors.extend(run_checkers(check_xml_parsing, html_items))
     errors.extend(run_checkers(check_raster_images, raster_images))
diff --git a/src/calibre/ebooks/oeb/polish/check/parsing.py b/src/calibre/ebooks/oeb/polish/check/parsing.py
index 4e3a2268db..c9ae875e0f 100644
--- a/src/calibre/ebooks/oeb/polish/check/parsing.py
+++ b/src/calibre/ebooks/oeb/polish/check/parsing.py
@@ -11,11 +11,11 @@ import re
 from lxml.etree import XMLParser, fromstring, XMLSyntaxError
 import cssutils
 
-from calibre import force_unicode
+from calibre import force_unicode, human_readable
 from calibre.ebooks.html_entities import html5_entities
 from calibre.ebooks.oeb.polish.pretty import pretty_script_or_style as fix_style_tag
 from calibre.ebooks.oeb.polish.utils import PositionFinder
-from calibre.ebooks.oeb.polish.check.base import BaseError, WARN, ERROR
+from calibre.ebooks.oeb.polish.check.base import BaseError, WARN, ERROR, INFO
 from calibre.ebooks.oeb.base import OEB_DOCS
 
 HTML_ENTITTIES = frozenset(html5_entities)
@@ -61,6 +61,16 @@ class NamedEntities(BaseError):
             f.write(nraw.encode('utf-8'))
         return True
 
+class TooLarge(BaseError):
+
+    level = INFO
+    MAX_SIZE = 260 *1024
+    HELP = _('This HTML file is larger than %s. Too large HTML files can cause performance problems'
+             ' on some ebook readers. Consider splitting this file into smaller sections.') % human_readable(MAX_SIZE)
+
+    def __init__(self, name):
+        BaseError.__init__(self, _('File too large'), name)
+
 class BadEntity(BaseError):
 
     HELP = _('This is an invalid (unrecognized) entity. Replace it with whatever'
@@ -103,6 +113,12 @@ class EntitityProcessor(object):
             self.bad_entities.append((m.start(), m.group()))
         return b' ' * len(m.group())
 
+def check_html_size(name, mt, raw):
+    errors = []
+    if len(raw) > TooLarge.MAX_SIZE:
+        errors.append(TooLarge(name))
+    return errors
+
 entity_pat = re.compile(br'&(#{0,1}[a-zA-Z0-9]{1,8});')
 
 def check_xml_parsing(name, mt, raw):