Skip removed images

2 files changed, 15 insertions, 13 deletions

diff --git a/Processing/Article_Builder.py b/Processing/Article_Builder.py
index 0e98c6f..5029150 100644
--- a/Processing/Article_Builder.py
+++ b/Processing/Article_Builder.py
@@ -4,6 +4,7 @@ from BeautifulSoup import Tag
 from NewtifulSoup import NewtifulStoneSoup as BeautifulStoneSoup

 from Processing.Article.Article_Data import *

 import re

+import os

 import logging

 

 logger = logging.getLogger('infoslicer')

@@ -126,9 +127,12 @@ def get_article_from_dita(image_path, dita):
             if tag.parent.name == "p":

                 source_article_id = article_id

                 text = image_path + '/' + tag['href']

-                picture_data = Picture_Data(source_article_id, text,

-                        tag['orig_href'])

-                sentence_data_list.insert(0, picture_data)

+                if not os.path.exists(text):

+                    logger.info('cannot find image %s' % text)

+                else:

+                    picture_data = Picture_Data(source_article_id, text,

+                            tag['orig_href'])

+                    sentence_data_list.insert(0, picture_data)

             

     article_title = input.find("title").renderContents().replace("\n", "").strip()

     

@@ -141,7 +145,10 @@ def get_article_from_dita(image_path, dita):
                 caption = caption.renderContents().replace("\n", "").strip()

             else:

                 caption = ""

-            image_list.append((img['href'], caption, img['orig_href']))

+            if not os.path.exists(os.path.join(image_path, img['href'])):

+                logger.info('cannot find image %s' % img['href'])

+            else:

+                image_list.append((img['href'], caption, img['orig_href']))

     

     data = Article_Data(article_id, article_id, article_title, "theme", section_data_list, image_list)                   

     

@@ -154,7 +161,6 @@ def get_dita_from_article(image_path, article):
     It calls the getData method of the article class to get the article_data representation of the article.

     It then constructs the corresponding DITA representation of the article.

     """

-    image_sources = {}

     article_data = article.getData()

     output = BeautifulStoneSoup("<?xml version='1.0' encoding='utf-8'?><!DOCTYPE reference PUBLIC \"-//IBM//DTD DITA IBM Reference//EN\" \"ibm-reference.dtd\"><reference><title>%s</title><prolog></prolog></reference>" % article_data.article_title)

     current_ref = output.reference            

@@ -200,7 +206,6 @@ def get_dita_from_article(image_path, article):
                         # switch image to relative path

                         text = sentence.text.replace(image_path, '') \

                                 .lstrip('/')

-                        image_sources[text.split('/')[0]] = None

                         image_tag = _tag_generator(output,

                                 "image", attrs=[("href", text),

                                                 ('orig_href', sentence.orig)])

@@ -225,7 +230,7 @@ def get_dita_from_article(image_path, article):
             image_list_body.append(image_tag)

     dita = output.prettify()

 

-    return (dita, image_sources)

+    return dita

             

 def _tag_generator(soup, name, attrs=[], contents=None):

     if attrs != []:

diff --git a/book.py b/book.py
index e3ad208..d01fea1 100644
--- a/book.py
+++ b/book.py
@@ -60,8 +60,8 @@ class Book(gobject.GObject):
         if entry:
             content = self._load(entry['uid'])
             if content:
-                data = Article_Builder.get_article_from_dita(image_root,
-                        content)
+                data = Article_Builder.get_article_from_dita(
+                        image_root, content)
                 self._article = Article(data)
             else:
                 self._article = Article()
@@ -253,10 +253,7 @@ class CustomBook(Book):
         self.find_by_uuid(self._article.uid)['title'] = \
                 self._article.article_title
 
-        contents, image_sources = Article_Builder.get_dita_from_article(
+        contents = Article_Builder.get_dita_from_article(
                 image_root, self._article)
 
-        #for i in image_sources.keys():
-        #    image_sources[i] = wiki[i].
-
         self._save(self._article.uid, contents)