half-functional lyx2lyx reversion

[lyx.git] / lib / lyx2lyx / parser_tools.py

diff --git a/lib/lyx2lyx/parser_tools.py b/lib/lyx2lyx/parser_tools.py
index 9a01514ef8ce43955f9bd066ce55be450444ba5d..e32ac5dc4fca7d879a933e8f9c0d7550aa800716 100644 (file)
--- a/lib/lyx2lyx/parser_tools.py
+++ b/lib/lyx2lyx/parser_tools.py
@@ -1,6 +1,6 @@
 # This file is part of lyx2lyx
 # -*- coding: utf-8 -*-
-# Copyright (C) 2002-2010 Dekel Tsur <dekel@lyx.org>, 
+# Copyright (C) 2002-2011 Dekel Tsur <dekel@lyx.org>, 
 # José Matos <jamatos@lyx.org>, Richard Heck <rgheck@comcast.net>
 #
 # This program is free software; you can redistribute it and/or
@@ -15,7 +15,7 @@
 #
 # You should have received a copy of the GNU General Public License
 # along with this program; if not, write to the Free Software
-# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA  02111-1307, USA.
+# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA
 
 
 ''' 
@@ -23,23 +23,27 @@ This modules offer several free functions to help parse lines.
 More documentaton is below, but here is a quick guide to what 
 they do. Optional arguments are marked by brackets.
 
-find_token(lines, token, start[, end[, exact]]):
+find_token(lines, token, start[, end[, ignorews]]):
   Returns the first line i, start <= i < end, on which
   token is found at the beginning. Returns -1 if not 
-  found. If exact is (given and) True, then differences
-  in whitespace do not count.
+  found. 
+  If ignorews is (given and) True, then differences
+  in whitespace do not count, except that there must be no 
+  extra whitespace following token itself.
 
 find_token_exact(lines, token, start[, end]):
-  Badly named. As find_token, but with ignorews True.
+  As find_token, but with ignorews True.
 
 find_tokens(lines, tokens, start[, end[, ignorews]]):
   Returns the first line i, start <= i < end, on which
   oen of the tokens in tokens is found at the beginning. 
-  Returns -1 if not found. If ignorews is (given and) True, 
-  then differences in whitespace do not count.
+  Returns -1 if not found. 
+  If ignorews is (given and) True, then differences
+  in whitespace do not count, except that there must be no 
+  extra whitespace following token itself.
 
 find_tokens_exact(lines, token, start[, end]):
-  Badly named. As find_tokens, but with ignorews True.
+  As find_tokens, but with ignorews True.
   
 find_token_backwards(lines, token, start):
 find_tokens_backwards(lines, tokens, start):
@@ -65,6 +69,11 @@ get_quoted_value(lines, token, start[, end[, default]):
   value, if they are present. So use this one for cases
   where the value is normally quoted.
 
+get_option_value(line, option):
+  This assumes we have a line with something like:
+      option="value"
+  and returns value. Returns "" if not found.
+
 del_token(lines, token, start[, end]):
   Like find_token, but deletes the line if it finds one.
   Returns True if a line got deleted, otherwise False.
@@ -133,6 +142,8 @@ is_nonempty_line(line):
 
 '''
 
+import re
+
 # Utilities for one line
 def check_token(line, token):
     """ check_token(line, token) -> bool
@@ -152,14 +163,15 @@ def is_nonempty_line(line):
 
 
 # Utilities for a list of lines
-def find_token(lines, token, start, end = 0, exact = False):
-    """ find_token(lines, token, start[[, end], exact]) -> int
+def find_token(lines, token, start, end = 0, ignorews = False):
+    """ find_token(lines, token, start[[, end], ignorews]) -> int
 
     Return the lowest line where token is found, and is the first
     element, in lines[start, end].
     
-    If exact is True (default is False), then differences in
-    whitespace are ignored.
+    If ignorews is True (default is False), then differences in
+    whitespace are ignored, except that there must be no extra
+    whitespace following token itself.
 
     Return -1 on failure."""
 
@@ -167,7 +179,7 @@ def find_token(lines, token, start, end = 0, exact = False):
         end = len(lines)
     m = len(token)
     for i in xrange(start, end):
-        if exact:
+        if ignorews:
             x = lines[i].split()
             y = token.split()
             if len(x) < len(y):
@@ -184,8 +196,8 @@ def find_token_exact(lines, token, start, end = 0):
     return find_token(lines, token, start, end, True)
 
 
-def find_tokens(lines, tokens, start, end = 0, exact = False):
-    """ find_tokens(lines, tokens, start[[, end], exact]) -> int
+def find_tokens(lines, tokens, start, end = 0, ignorews = False):
+    """ find_tokens(lines, tokens, start[[, end], ignorews]) -> int
 
     Return the lowest line where one token in tokens is found, and is
     the first element, in lines[start, end].
@@ -196,7 +208,7 @@ def find_tokens(lines, tokens, start, end = 0, exact = False):
 
     for i in xrange(start, end):
         for token in tokens:
-            if exact:
+            if ignorews:
                 x = lines[i].split()
                 y = token.split()
                 if len(x) < len(y):
@@ -294,6 +306,24 @@ def get_quoted_value(lines, token, start, end = 0, default = ""):
     return val.strip('"')
 
 
+def get_option_value(line, option):
+    rx = option + '\s*=\s*"([^"]+)"'
+    rx = re.compile(rx)
+    m = rx.search(line)
+    if not m:
+      return ""
+    return m.group(1)
+
+
+def set_option_value(line, option, value):
+    rx = '(' + option + '\s*=\s*")[^"]+"'
+    rx = re.compile(rx)
+    m = rx.search(line)
+    if not m:
+        return line
+    return re.sub(rx, '\g<1>' + value + '"', line)
+
+
 def del_token(lines, token, start, end = 0):
     """ del_token(lines, token, start, end) -> int