From b8c6cb836737d7cdcdaa47b4143f0c4d1de15e09 Mon Sep 17 00:00:00 2001
From: "yusuke.shinyama.dummy"
 <yusuke.shinyama.dummy@1aa58f4a-7d42-0410-adbc-911cccaed67c>
Date: Wed, 26 Aug 2009 15:20:44 +0000
Subject: [PATCH] git-svn-id:
 https://pdfminerr.googlecode.com/svn/trunk/pdfminer@129
 1aa58f4a-7d42-0410-adbc-911cccaed67c

---
 docs/index.html       | 12 +++++++-----
 pdfminer/converter.py | 14 +++++++++-----
 pdfminer/pdfdevice.py |  2 +-
 pdfminer/pdfinterp.py | 13 +++++++++++--
 4 files changed, 28 insertions(+), 13 deletions(-)

diff --git a/docs/index.html b/docs/index.html
index 2e0a7a6..45ff9af 100644
--- a/docs/index.html
+++ b/docs/index.html
@@ -18,7 +18,7 @@ Python PDF parser and analyzer
 
 <div align=right class=lastmod>
 <!-- hhmts start -->
-Last Modified: Mon Aug 24 15:56:08 JST 2009
+Last Modified: Thu Aug 27 00:20:29 JST 2009
 <!-- hhmts end -->
 </div>
 
@@ -101,6 +101,7 @@ World
 </ol>
 
 <p>
+<a name="cmap"></a>
 <h3>For non-ASCII languages</h3>
 In order to handle non-ASCII languages (e.g. Japanese),
 you need to install an additional data called <code>CMap</code>,
@@ -115,17 +116,16 @@ http://www.unixuser.org/~euske/pub/CMap.tar.bz2
 </a>
 <li> Expand the archive and put the <code>CMap</code> directory under the directory 
 where <code>pdfminer</code> is installed.
-(Normally this should be something like <code>/usr/lib/python2.5/site-packages</code>.)
+(Normally this should be something like <code>/usr/lib/python2.5/site-packages/pdfminer</code>.)
 For example:
 <blockquote><pre>
-$ <strong>cd /usr/lib/python2.5/site-packages</strong>
+$ <strong>cd /usr/lib/python2.5/site-packages/pdfminer</strong>
 $ <strong>tar jxf CMap.tar.bz2</strong>
 </pre></blockquote>
-<li> Do the following. (this is optional, but highly recommended)<br>
+<li> Do the following. (this is optional and may take several minutes, but highly recommended!)<br>
 <blockquote><pre>
 $ <strong>python -m pdfminer.cmap</strong>
 </pre></blockquote>
-This may take several minutes.
 </ol>
 
 <a name="usage"></a>
@@ -319,6 +319,8 @@ no stream header is displayed for the ease of saving it to a file.
 <hr noshade>
 <h2>Changes</h2>
 <ul>
+<li> 2009/08/27: Fixed page rotation handling.
+<li> 2009/08/26: Fixed zlib decoding bug. Thanks to Shon Urbas.
 <li> 2009/08/24: Fixed a bug in character placing. Thanks to Pawan Jain.
 <li> 2009/07/21: Improvement in layout analysis.
 <li> 2009/07/11: Improvement in layout analysis. Thanks to Lubos Pintes.
diff --git a/pdfminer/converter.py b/pdfminer/converter.py
index 24e37b1..4bc08c8 100644
--- a/pdfminer/converter.py
+++ b/pdfminer/converter.py
@@ -33,7 +33,7 @@ class TagExtractor(PDFDevice):
     self.outfp.write(enc(text, self.codec))
     return
 
-  def begin_page(self, page):
+  def begin_page(self, page, ctm):
     (x0, y0, x1, y1) = page.mediabox
     bbox = '%.3f,%.3f,%.3f,%.3f' % (x0, y0, x1, y1)
     self.outfp.write('<page id="%s" bbox="%s" rotate="%d">' %
@@ -77,8 +77,12 @@ class PDFPageAggregator(PDFTextDevice):
     self.stack = []
     return
 
-  def begin_page(self, page):
-    self.cur_item = LTPage(self.pageno, page.mediabox, page.rotate)
+  def begin_page(self, page, ctm):
+    (x0,y0,x1,y1) = page.mediabox
+    (x0,y0) = apply_matrix_pt(ctm, (x0,y0))
+    (x1,y1) = apply_matrix_pt(ctm, (x1,y1))
+    mediabox = (0, 0, abs(x0-x1), abs(y0-y1))
+    self.cur_item = LTPage(self.pageno, mediabox)
     return
   
   def end_page(self, _):
@@ -225,10 +229,11 @@ class HTMLConverter(PDFConverter):
   def end_page(self, page):
     def render(item):
       if isinstance(item, LTPage):
+        self.yoffset += item.y1
         self.write_rect('gray', 1, item.x0, self.yoffset-item.y1, item.width, item.height)
         if self.showpageno:
           self.outfp.write('<div style="position:absolute; top:%dpx;">' %
-                           ((self.yoffset-page.y1)*self.scale))
+                           ((self.yoffset-item.y1)*self.scale))
           self.outfp.write('<a name="%s">Page %s</a></div>\n' % (page.id, page.id))
         for child in item:
           render(child)
@@ -256,7 +261,6 @@ class HTMLConverter(PDFConverter):
           render(child)
       return
     page = PDFConverter.end_page(self, page)
-    self.yoffset += page.y1
     render(page)
     self.yoffset += self.pagepad
     return
diff --git a/pdfminer/pdfdevice.py b/pdfminer/pdfdevice.py
index 3713fcf..896ca8e 100644
--- a/pdfminer/pdfdevice.py
+++ b/pdfminer/pdfdevice.py
@@ -32,7 +32,7 @@ class PDFDevice(object):
   def do_tag(self, tag, props=None):
     return
 
-  def begin_page(self, page):
+  def begin_page(self, page, ctm):
     return
   def end_page(self, page):
     return
diff --git a/pdfminer/pdfinterp.py b/pdfminer/pdfinterp.py
index 967a62d..6c24a20 100644
--- a/pdfminer/pdfinterp.py
+++ b/pdfminer/pdfinterp.py
@@ -690,8 +690,17 @@ class PDFPageInterpreter(object):
   def process_page(self, page):
     if 1 <= self.debug:
       print >>stderr, 'Processing page: %r' % page
-    self.device.begin_page(page)
-    self.render_contents(page.resources, page.contents)
+    (x0,y0,x1,y1) = page.mediabox
+    if page.rotate == 90:
+      ctm = (0,-1,1,0, -y0,x1)
+    elif page.rotate == 180:
+      ctm = (-1,0,0,-1, x1,y1)
+    elif page.rotate == 270:
+      ctm = (0,1,-1,0, x0,-y1)
+    else:
+      ctm = (1,0,0,1, -x0,-y0)
+    self.device.begin_page(page, ctm)
+    self.render_contents(page.resources, page.contents, ctm=ctm)
     self.device.end_page(page)
     return