X-Git-Url: https://source.tree.se/git?p=treecutter.git;a=blobdiff_plain;f=treecutter%2Fdocbook.py;fp=treecutter%2Fdocbook.py;h=fd822ce8fe2cf6058fafa7528c56e0af0e38e0c8;hp=0000000000000000000000000000000000000000;hb=b011c30d2ca867e3e68451c7a3bfced704216fc1;hpb=369be7201d9703391d90d488cca8862b903ef15e

diff --git a/treecutter/docbook.py b/treecutter/docbook.py
new file mode 100644
index 0000000..fd822ce
--- /dev/null
+++ b/treecutter/docbook.py
@@ -0,0 +1,133 @@
+#!/usr/bin/python
+
+import os
+import subprocess
+
+from lxml import etree
+from lxml.builder import ElementMaker
+
+from pkg_resources import resource_filename, resource_listdir
+from time import time
+
+import treecutter.constants as const
+from treecutter.image import Image
+
+class Docbook():
+    """Class representing a docbook document"""
+    def __init__(self,filename):
+        self._filename = filename
+        self._doc = etree.parse(self._filename)
+        self._dirname = os.path.dirname(self._filename)
+
+    def title(self):
+        t = self._doc.xpath(u'/db:article/db:info/db:title',namespaces=const.XPATH)
+        if t:
+            t = unicode(t[0].text)
+        ta = self._doc.xpath(u'/db:article/db:info/db:titleabbrev',namespaces=const.XPATH)
+        if ta:
+           ta = unicode(ta[0].text)
+        return (t, ta)
+
+    def expand_imageobjects(self):
+        db = ElementMaker(namespace=const.DB_NS, nsmap=const.NSMAP)
+        images  = self._doc.xpath(u"//db:imageobject/db:imagedata[@fileref]",namespaces=const.XPATH)
+        for io in images:
+            image = Image(io)
+            link = db.link(image.infostr(),**{const.XLINK+"href": f})
+            io = db.imageobject(
+                db.imagedata(fileref=image.format(800,600), width=str(800), depth=str(600)),
+                db.caption(db.para(image.caption())))
+
+    def parse_xincludes(self):
+        cwd = os.getcwd()
+        for c in self._doc.xpath(u"//xi:include[@parse='text']",namespaces=const.XPATH):
+            href = c.get('href')
+            alang = c.get('accept-language')
+            xpointer = c.get('xpointer')
+            (p, ext) = os.path.splitext(href)
+            if ext in const.valid_scripts:
+                exe = []
+                script = os.path.join(os.path.abspath(self._dirname)+'/'+href)
+                if os.path.isfile(script):
+                    exe.append(script)
+                else:
+                    if href in resource_listdir('xinclude', ''):
+                        script = resource_filename('xinclude', href)
+                        exe.append(script)
+                    else:
+                        print "Script "+href+" in "+self._filename+" missing"
+                if alang:
+                    exe.append("lang="+alang)
+                if xpointer:
+                    exe.append("xptr="+xpointer)
+                print "  executing %15s" % (href),
+                ts = time()
+                os.chdir(self._dirname)
+                xml = subprocess.Popen(exe,stdout=subprocess.PIPE,
+                                       stderr=subprocess.PIPE)
+                (stdout, stderr) = xml.communicate()
+                #print xml.returnvalue
+                if stderr:
+                    print " ".join(exe)+" ERROR : [ "+stderr+" ]"
+                    exit
+                os.chdir(cwd)
+                te = time()
+                print " [%5.2f s]  (%s)" % (round(te-ts,2),xpointer)
+                xstr = etree.fromstring(stdout)
+# inserting the generated code and remove the xinclude reference
+                idp = c.getparent()
+                idp.insert(idp.index(c)+1,xstr)
+                idp.remove(c)
+
+    def collect_links(self):
+        res = []
+        for r in self._doc.xpath(u"//db:link[@xlink:href]",namespaces=const.XPATH):
+            rf = os.path.join(self._dirname,r.get(const.XLINK+'href'))
+            if os.path.isfile(rf):
+                if r.get('security')=='encrypt':
+                    with open(rf, 'rb') as f:
+                        gpg = gnupg.GPG()
+                        status = gpg.encrypt_file(
+                        f, None, passphrase=getpass.getpass(rf+' password:'), symmetric=True,
+                        output=rf+'.gpg')
+                    r.set(const.XLINK+'href', r.get(const.XLINK+'href')+'.gpg')
+                    rf=rf+'.gpg'
+                res.append(rf)
+        return res
+
+    def collect_images(self):
+        res = []
+        for i in self._doc.xpath(u"//db:imagedata[@fileref]",namespaces=const.XPATH):
+            im = os.path.join(self._dirname,i.get('fileref'))
+            if os.path.isfile(im):
+                res.append(im)
+            else:
+                print "WARNING: File "+im+" is missing!"
+        return res
+
+    def collect_forms(self):
+        res = []
+        for i in self._doc.xpath(u"//html:form[@action]",namespaces=const.XPATH):
+            pyscript = re.split('\.py',i.get('action'),1)[0]+'.py'
+            im = os.path.join(self._dirname,pyscript)
+            if os.path.isfile(im):
+                res.append(im)
+        return res
+
+    def tostring(self):
+        return etree.tostring(self._doc,encoding='UTF-8',pretty_print=False)
+
+    def xslt(self,transform):
+        return etree.tostring(transform(self._doc))
+
+    def clean(self):
+        def recursively_empty(e):
+            if e.text:
+                return False
+            return all((recursively_empty(c) for c in e.iterchildren()))
+
+        context = etree.iterwalk(self._doc)
+        for action, elem in context:
+            parent = elem.getparent()
+            if recursively_empty(elem):
+                parent.remove(elem)