From f85ba4e3261b4e64c84722087471824fbf12278e Mon Sep 17 00:00:00 2001
From: John Schember <john@nachtimwald.com>
Date: Fri, 14 Jan 2011 21:15:34 -0500
Subject: [PATCH] Fix sr key. Change footer and header removal to generic
 search and replace options.

---
 src/calibre/ebooks/conversion/cli.py        |  2 +-
 src/calibre/ebooks/conversion/plumber.py    |  9 ++---
 src/calibre/ebooks/conversion/preprocess.py | 42 +++++++++++----------
 3 files changed, 26 insertions(+), 27 deletions(-)

diff --git a/src/calibre/ebooks/conversion/cli.py b/src/calibre/ebooks/conversion/cli.py
index 91f0f95348..db1ec0857d 100644
--- a/src/calibre/ebooks/conversion/cli.py
+++ b/src/calibre/ebooks/conversion/cli.py
@@ -183,7 +183,7 @@ def add_pipeline_options(parser, plumber):
               }
 
     group_order = ['', 'LOOK AND FEEL', 'HEURISTICS',
-            'SEARCH AND REPLACE' 'STRUCTURE DETECTION',
+            'SEARCH AND REPLACE', 'STRUCTURE DETECTION',
             'TABLE OF CONTENTS', 'METADATA', 'DEBUG']
 
     for group in group_order:
diff --git a/src/calibre/ebooks/conversion/plumber.py b/src/calibre/ebooks/conversion/plumber.py
index 2e88baea4e..a12dbd48e1 100644
--- a/src/calibre/ebooks/conversion/plumber.py
+++ b/src/calibre/ebooks/conversion/plumber.py
@@ -540,8 +540,7 @@ OptionRecommendation(name='sr1_search',
     
 OptionRecommendation(name='sr1_replace',
     recommended_value='', level=OptionRecommendation.LOW,
-    help=_('Replace characters (can be lambda expression) to '
-           'replace the text found with sr1-search.')),
+    help=_('Replace characters to replace the text found with sr1-search.')),
 
 OptionRecommendation(name='sr2_search',
     recommended_value='', level=OptionRecommendation.LOW,
@@ -550,8 +549,7 @@ OptionRecommendation(name='sr2_search',
 
 OptionRecommendation(name='sr2_replace',
     recommended_value='', level=OptionRecommendation.LOW,
-    help=_('Replace characters (can be lambda expression) to '
-           'replace the text found with sr2-search.')),
+    help=_('Replace characters to replace the text found with sr2-search.')),
 
 OptionRecommendation(name='sr3_search',
     recommended_value='', level=OptionRecommendation.LOW,
@@ -560,8 +558,7 @@ OptionRecommendation(name='sr3_search',
 
 OptionRecommendation(name='sr3_replace',
     recommended_value='', level=OptionRecommendation.LOW,
-    help=_('Replace characters (can be lambda expression) to '
-           'replace the text found with sr3-search.')),
+    help=_('Replace characters to replace the text found with sr3-search.')),
 ]
         # }}}
 
diff --git a/src/calibre/ebooks/conversion/preprocess.py b/src/calibre/ebooks/conversion/preprocess.py
index 08a46cb8d9..35a311d58f 100644
--- a/src/calibre/ebooks/conversion/preprocess.py
+++ b/src/calibre/ebooks/conversion/preprocess.py
@@ -436,27 +436,29 @@ class HTMLPreProcessor(object):
         if not getattr(self.extra_opts, 'keep_ligatures', False):
             html = _ligpat.sub(lambda m:LIGATURES[m.group()], html)
 
+        if getattr(self.extra_opts, 'sr3_search', None):
+            try:
+                rules.insert(0,  (re.compile(self.extra_opts.sr3_search), self.extra_opts.sr3_replace))
+            except:
+                import traceback
+                print 'Failed to parse sr3-search regexp'
+                traceback.print_exc()
+        if getattr(self.extra_opts, 'sr2_search', None):
+            try:
+                rules.insert(0, (re.compile(self.extra_opts.sr2_search), self.extra_opts.sr2_replace))
+            except:
+                import traceback
+                print 'Failed to parse sr2-search regexp'
+                traceback.print_exc()
+        if getattr(self.extra_opts, 'sr1_search', None):
+            try:
+                rules.insert(0, (re.compile(self.extra_opts.sr1_search), self.extra_opts.sr1_replace))
+            except:
+                import traceback
+                print 'Failed to parse sr1-search regexp'
+                traceback.print_exc()
+
         end_rules = []
-        if getattr(self.extra_opts, 'remove_header', None):
-            try:
-                rules.insert(0,
-                    (re.compile(self.extra_opts.header_regex), lambda match : '')
-                )
-            except:
-                import traceback
-                print 'Failed to parse remove_header regexp'
-                traceback.print_exc()
-
-        if getattr(self.extra_opts, 'remove_footer', None):
-            try:
-                rules.insert(0,
-                    (re.compile(self.extra_opts.footer_regex), lambda match : '')
-                )
-            except:
-                import traceback
-                print 'Failed to parse remove_footer regexp'
-                traceback.print_exc()
-
         # delete soft hyphens - moved here so it's executed after header/footer removal
         if is_pdftohtml:
             # unwrap/delete soft hyphens