Changeset 824

Timestamp:

06/12/07 14:08:16 (2 years ago)

Author:

thomase

Message:

Better xpath construction using namespaces. Copy all the nodes we need from the library, including related works information.

Files:

• BADataMunger/trunk/modsmixer.py (modified) (9 diffs)

BADataMunger/trunk/modsmixer.py

@@ -2 +2 @@
-
-import lxml.etree as etree
+
+MODS = "http://www.loc.gov/mods/v3"
+XLINK = "http://www.w3.org/1999/xlink"
+NSD = {'mods': MODS, 'xlink': XLINK}
-
-def flatten(text, addit=u''):
@@ -27 +31 @@
-        f = open(student)
-        content = f.read()
+        content = content.replace('<modsCollection xmlns="http://www.loc.gov/mods/v3">', '<modsCollection xmlns="http://www.loc.gov/mods/v3" xmlns:xlink="http://www.w3.org/1999/xlink">')
-        f.close()
-        self.student = etree.XML(content)
@@ -32 +37 @@
-        content = f.read()
-        f.close()
+        content = content.replace('<modsCollection>', '<modsCollection xmlns="http://www.loc.gov/mods/v3" xmlns:xlink="http://www.w3.org/1999/xlink">')
-        self.library = etree.XML(content)
-        
-*[local-name()='mods']"
+mods:mods", NSD
-        for snode in snodes:
-*[local-name()='titleInfo' and @type='abbreviated']/*[local-name()='title']"
+mods:titleInfo[@type='abbreviated']/mods:title", NSD
-            s_short_title = u' '.join(s_short_title_node[0].text.replace('\n', ' ').strip().split())
-*[local-name()='titleInfo' and not(@type)]/*[local-name()='title']"
+mods:titleInfo[not(@type)]/mods:title", NSD
-            try:
-                s_title = u' '.join(s_title_node.text.replace('\n', ' ').strip().split())
@@ -44 +50 @@
-                print 'Something is wrong with the student title node for short_title = %s' % s_short_title
-            
-/titleInfo[@type='abbreviated']/title[normalize-space(.) = '%s']/ancestor:
-
+:mods/mods:titleInfo[@type='abbreviated']/mods:title[normalize-space(.) = '%s']/ancestor::mods
+, NSD
-            if len(lnodes) > 1:
-                
-/titleInfo[@type='uniform']/title[normalize-space(.) = '%s']/ancestor:
-
+:mods/mods:titleInfo[@type='uniform']/mods:title[normalize-space(.) = '%s']/ancestor::mods
+, NSD
-                if len(lnodes) == 1:
-titleInfo[@type='abbreviated']/title[normalize-space(.) = '%s']/ancestor::mods" % s_short_title
+mods:titleInfo[@type='abbreviated']/mods:title[normalize-space(.) = '%s']/ancestor::mods:mods" % s_short_title, NSD
-                        print "found match in library on full title '%s', but short title did not match '%s'" % (s_title, s_short_title)
-
+, NSD
-                elif len(lnodes) > 1:
-                    print "found multiple matches on long title in library for '%s = %s" % (s_short_title.encode('latin', 'xmlcharrefreplace'), s_title.encode('latin', 'xmlcharrefreplace'))
@@ -59 +65 @@
-                    print "found multiple matches in on short title library for '%s = %s" % (s_short_title.encode('latin', 'xmlcharrefreplace'), s_title.encode('latin', 'xmlcharrefreplace'))
-            if len(lnodes) == 0:
-*[local-name()='mods']
+mods:mods
-                if len(snode.xpath(squery)) == 0:
-                    print "    notice: unmatched article '%s'" % s_short_title.encode('latin', 'xmlcharrefreplace')
@@ -67 +73 @@
-                # one match, so gather up all the data we will need
-                lnode = lnodes[0]
-titleInfo[@type='uniform']/title"
+mods:titleInfo[@type='uniform']/mods:title", NSD
-                try:
-                    l_title_node = l_title_nodes[0]
@@ -83 +89 @@
-                if len(lnode.xpath("./@ID")) > 0:
-                    snode.attrib['ID'] = lnode.attrib['ID']
+                else:
+                    print "no ID!!!!"
-
-                # proper title type attributes
@@ -137 +145 @@
-                if l_title_lang.strip() != '':
-                    # add xml:lang attribute to existing title on scholar
-
+xpath('..')[0].
-                else:
-                    print "No title language found for '%s'\n" % s_short_title.encode('latin1', 'xmlcharrefreplace')
@@ -143 +151 @@
-                # copy over items verbatim from library record to student record
-                nodestocopy = []
-name"
-typeOfResource"
-genre"
-originInfo"
-relatedItem"
-identifier"
-location"
+mods:name", NSD
+mods:typeOfResource", NSD
+mods:genre", NSD
+mods:originInfo", NSD
+mods:relatedItem", NSD
+mods:identifier", NSD
+mods:location", NSD
-                
-                if len(nodestocopy) > 0:
-                    for node in nodestocopy:
-                        snode.append(node)
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-        pcontent = etree.tostring(self.student).encode('utf-8')
+        pcontent = '<?xml version="1.0" encoding="UTF-8"?>\n' + pcontent
-        f = open(destination, 'w')
-        f.write(pcontent)