Finished converting the structure to docbook.

4 files changed, 64 insertions, 17 deletions

diff --git a/ooo-help-parser.py b/ooo-help-parser.py
index 0a297b6..bba303e 100755
--- a/ooo-help-parser.py
+++ b/ooo-help-parser.py
@@ -77,6 +77,8 @@ def main ():
     parser.set_defaults(output=None)
     parser.add_option("-o", "--output", dest="output", help="write output to FILE", metavar="FILE")
     parser.add_option("-t", "--tree-dir", dest="tree_dir", help="Directory where the tree files are located.  Tree files are expected to have .tree extension.")
+    parser.add_option("--debug-tree", action="store_true", dest="debug_tree",
+        help="Output the tree structure for debugging purposes.", default=False)
     parser.add_option("--no-convert", action="store_false", dest="convert", 
         help="Don't convert to docbook but simply output the parsed raw xhp structure", default=True)
     options, args = parser.parse_args()
@@ -89,12 +91,6 @@ def main ():
         parser.print_help()
         sys.exit(1)
 
-    # Process the tree files first
-    treeroot = processTreeFiles(options.tree_dir)
-
-    # walk all directories and collect all files.
-    filepaths = walkDirs(args)
-
     fd = sys.stdout
     if options.output != None:
         if os.path.isdir(options.output):
@@ -102,6 +98,17 @@ def main ():
             sys.exit(1)
         fd = open(options.output, 'w')
 
+    # Process the tree files first
+    treeroot = processTreeFiles(options.tree_dir)
+    if options.debug_tree:
+        node.prettyPrint(fd, treeroot)
+        fd.close()
+        sys.exit(0)
+
+    # walk all directories and collect all files.
+    filepaths = walkDirs(args)
+
+
     xhproots, filesParsed = parseAllXHPFiles(filepaths)
 
     if options.convert:
diff --git a/source/docbook.py b/source/docbook.py
index cf2d648..2d69c33 100644
--- a/source/docbook.py
+++ b/source/docbook.py
@@ -101,14 +101,51 @@ class FilePathSorter:
                 self.__walkToContent(child)
 
 
+def appendDocBookElement (src):
+    if src.name == 'book':
+        return src.appendElement('chapter')
+    elif src.name == 'chapter':
+        return src.appendElement('sect1')
+    elif src.name == 'sect1':
+        return src.appendElement('sect2')
+    elif src.name == 'sect2':
+        return src.appendElement('sect3')
+    elif src.name == 'sect3':
+        return src.appendElement('sect4')
+    else:
+        return None
+
+
 class DocBookConverter:
+
     def __init__ (self, treeroot, xhproots):
         self.treeroot = treeroot
         self.xhproots = xhproots
         self.root = node.Root()
 
     def convert (self):
-        pass
+        book = self.root.appendElement('book')
+        bookinfo = book.appendElement('bookinfo')
+        title = bookinfo.appendElement('title')
+        title.appendContent("OpenOffice.org Help")
+        
+        for section in self.treeroot.getChildNodes():
+            self.__walk(section, book)
+
+    def __walk (self, src, dest):
+        # src element is either 'section' or 'content'.
+        if src.name == 'section':
+            title = src.getAttr('title')
+            elem = appendDocBookElement(dest)
+            elem.appendElement('title').appendContent(title)
+            for child in src.getChildNodes():
+                self.__walk(child, elem)
+        elif src.name == 'content':
+            # this element has 'title' and 'path' attributes, and has no more child nodes.
+            title = src.getAttr('title')
+            elem = appendDocBookElement(dest)
+            elem.appendElement('title').appendContent(title)
+
 
     def prettyPrint (self, fd):
         node.prettyPrint(fd, self.root)
diff --git a/source/node.py b/source/node.py
index dc37dcb..8dcbb27 100644
--- a/source/node.py
+++ b/source/node.py
@@ -1,3 +1,4 @@
+import sys
 
 class NodeType:
     Unknown = 0
@@ -78,7 +79,7 @@ class Element(NodeBase):
                 text += child.getContent()
         return text
 
-    def getAttrByName (self, name):
+    def getAttr (self, name):
         if not self.attrs.has_key(name):
             return None
         return self.attrs[name]
@@ -89,7 +90,9 @@ class Element(NodeBase):
 encodeTable = {
     '>': 'gt',
     '<': 'lt',
-    '&': 'amp'
+    '&': 'amp',
+    '"': 'quot',
+    '\'': 'apos'
 }
 
 def encodeString (sin):
@@ -132,9 +135,8 @@ def printNode (fd, node, level):
             keys = node.attrs.keys()
             keys.sort()
             for key in keys:
-                line += " " + key + '="' + node.attrs[key] + '"'
+                line += " " + key + '="' + encodeString(node.attrs[key]) + '"'
         if hasChildren:# and not nodesToSkip.has_key(node.name):
-            line = encodeString(line)
             line = "<%s>\n"%line
             fd.write (indent + line)
             for child in node.getChildNodes():
@@ -142,12 +144,10 @@ def printNode (fd, node, level):
             line = "</%s>\n"%node.name
             fd.write (indent + line)
         else:
-            line = encodeString(line)
             line = "<%s/>\n"%line
             fd.write (indent + line)
 
     elif node.nodeType == NodeType.Content:
         content = node.content.strip()
         if len(content) > 0:
-            content = encodeString(content)
             fd.write (indent + content + "\n")
diff --git a/source/tree.py b/source/tree.py
index f39a626..2d91637 100644
--- a/source/tree.py
+++ b/source/tree.py
@@ -18,7 +18,8 @@ class TreeBuilder:
                     continue
 
                 # help_section element has a 'title' attribute.
-                title = helpsection.getAttrByName('title')
+                title = helpsection.getAttr('title')
+                title = node.encodeString(title)
                 elem = self.root.appendElement('section')
                 elem.setAttr('title', title)
                 for child in helpsection.getChildNodes():
@@ -32,14 +33,16 @@ class TreeBuilder:
         if src.name == 'topic':
             # the 'id' attribute contains the corresponding xhp file path, while 
             # the content of this element is the title of this section.
-            xhppath = src.getAttrByName('id')
+            xhppath = src.getAttr('id')
             title = src.getContent()
-            elem = dest.appendElement('section')
+            title = node.encodeString(title)
+            elem = dest.appendElement('content')
             elem.setAttr('title', title)
             elem.setAttr('path', xhppath)
         elif src.name == 'node':
             # A 'node' element is just a branch point; it doesn't have any content.
-            title = src.getAttrByName('title')
+            title = src.getAttr('title')
+            title = node.encodeString(title)
             elem = dest.appendElement('section')
             elem.setAttr('title', title)
             for child in src.getChildNodes():