Changeset 458:48b135b089c8 in documentViewer for MpdlXmlTextServer.py

Timestamp:

Jul 19, 2011, 6:46:35 PM (13 years ago)

Author:

casties

Branch:

elementtree

Message:

more renovation

File:

• MpdlXmlTextServer.py (modified) (5 diffs)

MpdlXmlTextServer.py

@@ -13 +13 @@
 import logging
 import urllib
-import documentViewer
-#from documentViewer import getTextFromNode, serializeNode
-
-def intOr0(s, default=0):
-    """convert s to int or return default"""
-    try:
-        return int(s)
-    except:
-        return default
-
-def getText(node):
-    """get the cdata content of a node"""
-    if node is None:
-        return ""
-    # ET:
-    text = node.text or ""
-    for e in node:
-        text += gettext(e)
-        if e.tail:
-            text += e.tail
-
-    return text
+
+from SrvTxtUtils import getInt, getText, getHttpData
 
 def serialize(node):
@@ -91 +71 @@
         
     def __init__(self,id,title="",serverUrl="http://mpdl-text.mpiwg-berlin.mpg.de/mpdl/interface/", serverName=None, timeout=40):
-        
         """constructor"""
         self.id=id
@@ -103 +82 @@
     def getHttpData(self, url, data=None):
         """returns result from url+data HTTP request"""
-        return documentViewer.getHttpData(url,data,timeout=self.timeout)
+        return getHttpData(url,data,timeout=self.timeout)
     
     def getServerData(self, method, data=None):
         """returns result from text server for method+data"""
         url = self.serverUrl+method
-        return documentViewer.getHttpData(url,data,timeout=self.timeout)
+        return getHttpData(url,data,timeout=self.timeout)
 
     # WTF: what does this really do? can it be integrated in getPage?
@@ -269 +248 @@
             # pageNumberOrigNorm
             elif dc == 'countFigureEntries':
-                docinfo['countFigureEntries'] = intOr0(div.text)
+                docinfo['countFigureEntries'] = getInt(div.text)
                 
             # pageNumberOrigNorm
             elif dc == 'countTocEntries':
                 # WTF: s1 = int(s)/30+1
-                docinfo['countTocEntries'] = intOr0(div.text)
+                docinfo['countTocEntries'] = getInt(div.text)
                 
             # numTextPages
             elif dc == 'countPages':
-                np = intOr0(div.text)                    
+                np = getInt(div.text)                    
                 if np > 0:
                     docinfo['numTextPages'] = np
@@ -505 +484 @@
                 
             elif dc == 'queryResultHits':
-                docinfo['tocSize_%s'%mode] = intOr0(div.text)
+                docinfo['tocSize_%s'%mode] = getInt(div.text)
 
         if pagediv:
-#            # split xml in chunks
-#            tocs = []
-#            tocdivs = pagediv.findall('div')
-#            for p in zip(tocdivs[::2], tocdivs[1::2]):
-#                toc = serialize(p[0])
-#                toc += serialize(p[1])
-#                tocs.append(toc)
-#                logging.debug("pair: %s"%(toc))
             # store XML in docinfo
             docinfo['tocXML_%s'%mode] = ET.tostring(pagediv, 'UTF-8')