Debian Apache adaptation

- Proper UTF-8 handling
- .htaccess CGI and environment variables

.gitignore

@@ -3,3 +3,6 @@ test/
 input/
 images/
 .directory
+*.swp
+*~
+*.pyc

.htaccess

@@ -0,0 +1,3 @@
+SetEnv LANG en_US.UTF-8
+Options +ExecCGI
+AddHandler cgi-script .py

main.py

@@ -1,4 +1,4 @@
-#!/usr/bin/python
+#!/usr/bin/python3
 # -*- coding: UTF-8 -*-
 
 # GET me using a web browser,
@@ -85,8 +85,9 @@ except KeyError:
 result = tcparser.filter(library, title=title, author=author)
 
 if format == 'html':
-    html = tcparser.getHTML(result)
-    ET.dump(html)
+    htmlTree = tcparser.getHTML(result)
+    htmlString = ET.tostring(htmlTree.getroot(), encoding='unicode', method='html')
+    print(htmlString)
 if format == 'json':
     # Wanna get a pretty JSON encoded library to do your nasty things offline at home? ;-)
     print(json.dumps(result, indent=4))

tcparser.py

@@ -1,28 +1,23 @@
 import xml.etree.ElementTree as ET
 import json
 import datetime
+import sys
 
 # Parse Tellico's XML and get a library struct,
 # a stripped version of our library in a Python-friendly format
 def getLibrary(path, lastUpdate):
-    # Get XML string from file
-    fh = open(path)
-    xmlstring = fh.read()
-    # Get rid of XML namespace
-    xmlstring = xmlstring.replace('xmlns="http://periapsis.org/tellico/"', '')
+    namespace = {'tellico': 'http://periapsis.org/tellico/' }
 
-    root = ET.fromstring(xmlstring)
+    xml = ET.parse(path)
+    root = xml.getroot()
 
-    if root[0].tag != 'collection':
-        sys.exit('No collection found')
-
-    collection = root[0]
+    collection = root.find('tellico:collection', namespace)
 
     library = dict()
     library['lastupdate'] = lastUpdate
     library['books'] = list()
 
-    for i in collection.findall('entry'):
+    for i in collection.findall('tellico:entry', namespace):
         newbook = dict()
         newbook['id'] = int(i.attrib['id'])
         # these `for` overwrite previous values,
@@ -30,21 +25,21 @@ def getLibrary(path, lastUpdate):
         # actually there is no 1to1 conversion between XML and JSON, so this operation
         # can not be made automagically without doing some preliminary assumptions
         # (Possibly useful module: https://github.com/martinblech/xmltodict)
-        for j in i.iter('title'):
+        for j in i.iterfind('tellico:title', namespace):
             newbook['title'] = j.text
-        for j in i.iter('publisher'):
+        for j in i.iterfind('tellico:publisher', namespace):
             newbook['publisher'] = j.text
-        for j in i.iter('pub_year'):
+        for j in i.iterfind('tellico:pub_year', namespace):
             newbook['year'] = int(j.text)
-        for j in i.iter('isbn'):
+        for j in i.iterfind('tellico:isbn', namespace):
             newbook['isbn'] = j.text.replace('-', '')
-        for j in i.iter('pages'):
+        for j in i.iterfind('tellico:pages', namespace):
             newbook['pages'] = int(j.text)
-        for j in i.iter('cover'):
+        for j in i.iterfind('tellico:cover', namespace):
             newbook['cover'] = j.text
         newbook['authors'] = list()
-        for j in i.iter('authors'):
-            for k in j.findall('author'):
+        for j in i.iterfind('tellico:authors', namespace):
+            for k in j.findall('tellico:author', namespace):
                 newbook['authors'].append(k.text)
 
         library['books'].append(newbook)