X-Git-Url: https://git.mdrn.pl/redakcja.git/blobdiff_plain/7499a88c62e78c49d7f9e393b8e67a315acc16ba..b6b62a76505574e1961e15900a96a70a5461f108:/apps/catalogue/management/edumed.py

diff --git a/apps/catalogue/management/edumed.py b/apps/catalogue/management/edumed.py
index c384dac2..05034368 100644
--- a/apps/catalogue/management/edumed.py
+++ b/apps/catalogue/management/edumed.py
@@ -96,7 +96,7 @@ class Informacje(Tagger):
 
 class List(Tagger):
     point = re.compile(r"^[\s]*[-*·]{1,2}(.*)")
-    num = re.compile(r"^[\s]*[0-9a-z]{1,2}[.]\s+(.*)")
+    num = re.compile(r"^[\s]*[a-z][.]\s+(.*)")
 
     def __init__(self, *args):
 
@@ -137,7 +137,8 @@ class List(Tagger):
 class Paragraph(Tagger):
     remove_this = [
         re.compile(r"[\s]*opis zawarto.ci[\s]*", re.I),
-        re.compile(r"^[\s]*$")
+        re.compile(r"^[\s]*$"),
+        re.compile(r"http://pad.nowoczesnapolska.org.pl/p/slowniczek")
         ]
     podrozdzial = [
         re.compile(r"[\s]*(przebieg zaj..|opcje dodatkowe)[\s]*", re.I),
@@ -258,11 +259,12 @@ dc_fixed = {
     }
 
 
+class NotFound(Exception):
+    pass
+
+
 def find_block(content, title_re, begin=-1, end=-1):
     title_re = re.compile(title_re, re.I | re.UNICODE)
-    print "looking for %s" % title_re.pattern
-    if title_re.pattern[0:6] == 'pomoce':
-        import pdb; pdb.set_trace()
 
     rb = -1
     if begin < 0: begin = 0
@@ -286,11 +288,11 @@ def find_block(content, title_re, begin=-1, end=-1):
             break
     if rb >= 0:
         return rb, i
+    raise NotFound()
 
 
 def remove_block(content, title_re, removed=None):
     rb, re = find_block(content, title_re)
-
     if removed is not None and isinstance(removed, list):
         removed += content[rb:re][:]
     content[rb:re] = []
@@ -303,7 +305,7 @@ def mark_activities(content):
     is_przebieg = re.compile(r"[\s]*przebieg zaj..[\s]*", re.I)
 
     is_next_section = re.compile(r"^[IVX]+[.]? ")
-    is_activity = re.compile(r"^[0-9]+[.]? (.+)")
+    is_activity = re.compile(r"^[0-9]+[.] (.+)")
 
     is_activity_tools = re.compile(r"^pomoce:[\s]*(.+)")
     is_activity_work = re.compile(r"^forma pracy:[\s]*(.+)")
@@ -320,14 +322,16 @@ def mark_activities(content):
     ae = -1
     while True:
         e = content[i]
+        if isinstance(e, Section):
+            if in_activities and \
+                is_next_section.match(e.title):
+                in_activities = False
+            
         if isinstance(e, Paragraph):
             if not in_activities and \
                 is_przebieg.match(e.line):
                 in_activities = True
 
-            if in_activities and \
-                is_next_section.match(e.line):
-                in_activities = False
             if in_activities:
                 m = is_activity.match(e.line)
                 if m:
@@ -417,8 +421,14 @@ def toxml(content, pretty_print=False):
     # some transformations
     content = mark_activities(content)
     content = mark_dictionary(content)
-    content = remove_block(content, r"wykorzyst(yw)?ane metody[+ PA\[\].]*")
-    content = remove_block(content, r"(pomoce|potrzebne materia.y)[+ PA\[\]]*")
+    try:
+        content = remove_block(content, r"wykorzyst(yw)?ane metody[+ PA\[\].]*")
+    except NotFound:
+        pass
+    try:
+        content = remove_block(content, r"(pomoce|potrzebne materia.y)[+ PA\[\]]*")
+    except NotFound:
+        pass
     content = move_evaluation(content)
 
     info = content.pop(0)