Added Python library of various tools for making modules, and

specific script for creating a combined Calvin's Commentaries module


git-svn-id: https://www.crosswire.org/svn/sword-tools/trunk@89 07627401-56e2-0310-80f4-f8cd0041bdcd

3 files changed, 140 insertions, 0 deletions

diff --git a/modules/calvinscommentaries/README b/modules/calvinscommentaries/README
new file mode 100644
index 0000000..9f86798
--- /dev/null
+++ b/modules/calvinscommentaries/README
@@ -0,0 +1,45 @@
+
+Conversion of Calvin's commentaries into OSIS format and a Sword module
+
+Requirements:
+-------------
+- ThML sources: calcom??.xml files, as downloaded from CCEL.
+  For convenience, a recent version of the files can be downloaded here:
+  http://lukeplant.me.uk/misc/sword/calcom_sources.tar.bz2
+  Extract this file.
+- thml2osis.xslt from
+  http://crosswire.org/svn/sword-tools/trunk/thml2osis/xslt/
+- xsltproc for processing the above
+- Python for script that combines calcom??.xml files
+- Python swordutils library:
+   http://crosswire.org/svn/sword-tools/trunk/python
+  A checkout of this directory should be in your PYTHONPATH
+
+Make the module
+---------------
+
+$ ./combine_calcom.py calcom_sources/calcom??.xml
+(output stored in calvinscommentaries.thml)
+$ xsltproc --novalid path/to/thml2osis.xslt calvinscommentaries.thml > calvinscommentaries.osis
+
+TODO
+- convert OSIS commentary to Sword module
+
+Explanation of these steps
+--------------------------
+1) 'Correct' some of the ThML files.  In particular, change the
+   'scripCom' tags so that they enclose the text they refer to,
+   rather than just come at the beginning of it.
+   This is done as part of combine_calcom.py
+
+2) Combine all the ThML files into one big one, and at the same time:
+   - modify the header information, using one of the calcom??.xml files
+     as a template
+   - make any corrections necessary to the ThML for the new context
+
+   Output: calvinscommentaries.thml
+
+3) Convert to OSIS, using thml2osis.xslt
+
+4) TODO - convert to Sword module.  The current osis2mod utility expects
+   commentaries to be marked up like Bibles.
diff --git a/modules/calvinscommentaries/calvinscommentaries.conf b/modules/calvinscommentaries/calvinscommentaries.conf
new file mode 100644
index 0000000..b201b45
--- /dev/null
+++ b/modules/calvinscommentaries/calvinscommentaries.conf
@@ -0,0 +1,17 @@
+[CalvinsCommentaries]
+DataPath=./modules/comments/zcom/calvinscommentaries/
+ModDrv=zCom
+BlockType=CHAPTER
+SourceType=OSIS
+CompressType=ZIP
+Lang=en
+Description=Calvin's Collected Commentaries
+About=John Calvin's commentaries on many books of the Bible, collected \
+into a single volume from material found at Christian Classics Ethereal Library \par \
+Converted to Sword module format by Luke Plant <L.Plant.98@cantab.net>
+Version=1.0
+Encoding=UTF-8
+LCSH=Bible--Commentaries.
+DistributionLicense=Public Domain
+TextSource=http://www.ccel.org/
+MinimumVersion=1.5.2
diff --git a/modules/calvinscommentaries/combine_calcom.py b/modules/calvinscommentaries/combine_calcom.py
new file mode 100755
index 0000000..48be2eb
--- /dev/null
+++ b/modules/calvinscommentaries/combine_calcom.py
@@ -0,0 +1,78 @@
+#!/usr/bin/env python
+
+# Converts the source calcom??.xml files into a single
+# ThML file, with corrections made to allow it to be
+# used as a Sword module
+
+#------------------------------------------------------------
+# CONFIG
+
+PUBLISHERID = u"lukeplant.me.uk"
+
+#------------------------------------------------------------
+
+from xml.dom import minidom
+from xml import xpath
+from datetime import datetime
+from swordutils.xml import thml, utils
+from swordutils.xml.utils import RemoveNode, GeneralReplaceContents, ReplaceContents, do_replacements
+from swordutils.xml.combine import LazyNodes
+import sys
+
+
+now = datetime.now() # for general timestamping purposes
+
+
+def do_head_replacements(doc):
+    
+    corrections = {
+        "//DC.Title[@sub='Main']":        ReplaceContents(u"Calvin's Combined Commentaries"),
+        "//DC.Title[@sub='authTitle']":   RemoveNode(),
+        "//DC.Title[@sub='Alternative']": RemoveNode(),
+        "//printSourceInfo":              ReplaceContents(u"<published>Multiple printed works, Baker</published>"),
+        "//electronicEdInfo/bookID":      ReplaceContents(u"calvincommentaries"),
+        "//DC.Identifier":                RemoveNode(), # TODO - new identifier?
+        "//electronicEdInfo/editorialComments":
+          GeneralReplaceContents(lambda t: u"Multiple ThML files combined into single ThML file by a script.  Original editoral comments: " + t),
+        "//electronicEdInfo/revisionHistory":
+          GeneralReplaceContents(lambda t: unicode(now.strftime('%Y-%m-%d')) +   u": Multiple ThML files combined into single ThML file by a script. Original revision history:" + t),
+        "//electronicEdInfo/publisher": ReplaceContents(PUBLISHERID),
+
+    }
+    do_replacements(doc, corrections)
+
+def do_body_corrections(doc):
+    # Correct <scripCom>
+    rootNode = utils.getRoot(doc)
+    thml.expandScripComNodes(rootNode)
+    # Other corrections
+    corrections = {
+        # id attributes can now contain duplicates due to combination
+        # of multiple files, so we remove them all.
+        "//@id": RemoveNode(),
+
+    }
+    do_replacements(doc, corrections)
+
+def combine(templatefile, allfiles):
+    # Get the main one
+    templatexml = minidom.parse(templatefile)
+    mainBody = utils.getNodesFromXPath(templatexml, '//ThML.body')[0]
+    mainBody.childNodes = []
+    do_head_replacements(templatexml)
+    # The following childNodes will be lazily evaluated as
+    # templatexml.writexml iterates over them
+    mainBody.childNodes = LazyNodes(templatexml, allfiles, do_body_corrections, '//ThML.body')
+
+    fh = open('calvinscommentaries.thml', 'wb')
+    utils.writexml(templatexml, fh)
+    fh.close()
+
+def main(filenames):
+    combine(filenames[0], filenames)
+
+if __name__ == "__main__":
+    if len(sys.argv) < 2:
+        print "Usage: ./combine_and_correct.py filename.xml [filename2.xml ...]"
+        sys.exit(1)
+    main(sys.argv[1:])