Merge pull request #81 from ausgerechnet/v0.12.3

v0.12.3

.github/workflows/build-test.yml

@@ -1,4 +1,4 @@
-name: build & test
+name: Build & test using current Python versions
 
 on: [workflow_dispatch, push]
 

.github/workflows/publish.yml

@@ -1,4 +1,4 @@
-name: Create Dist & Publish on PyPI
+name: Create source distribution & publish on PyPI
 
 on:
   workflow_dispatch:
@@ -12,24 +12,23 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-    - uses: actions/checkout@v3
+    - uses: actions/checkout@v4
     - name: Install CWB
       run: |
         sudo apt-get install libncurses5-dev
-        svn co http://svn.code.sf.net/p/cwb/code/cwb/trunk cwb
-        cd cwb
-        sed -i 's/SITE=beta-install/SITE=standard/' config.mk
-        sudo ./install-scripts/install-linux
-        sudo ldconfig
+        wget https://kumisystems.dl.sourceforge.net/project/cwb/cwb/cwb-3.5/deb/cwb_3.5.0-1_amd64.deb
+        wget https://master.dl.sourceforge.net/project/cwb/cwb/cwb-3.5/deb/cwb-dev_3.5.0-1_amd64.deb
+        sudo apt-get install ./cwb_3.5.0-1_amd64.deb
+        sudo apt-get install ./cwb-dev_3.5.0-1_amd64.deb
     - name: Set up Python 3.12
-      uses: actions/setup-python@v4
+      uses: actions/setup-python@v5
       with:
         python-version: '3.12'
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
         make install
-    - name: Create Dist
+    - name: Create source distribution
       run: |
         make sdist
     - name: Publish

ccc/cwb.py

@@ -1477,15 +1477,15 @@ def correct_anchors(self, corrections):
         """
         self.df = correct_anchors(self.df, corrections)
 
-    def breakdown(self, p_atts=['word'], flags="", split=False):
+    def breakdown(self, p_atts=['word'], flags="", split=False, start='match', end='matchend'):
         """Frequency breakdown of match..matchend.
 
         """
 
         logger.info('creating frequency breakdown')
         breakdown = self.counts.dump(
             df_dump=self.df,
-            start='match', end='matchend',
+            start=start, end=end,
             p_atts=p_atts, split=split
         )
 

ccc/version.py

@@ -4,4 +4,4 @@
 
 """
 
-__version__ = "0.12.2"
+__version__ = "0.12.3"

tests/test_10_dumps.py

@@ -55,6 +55,13 @@ def test_breakdown_p_att(germaparl):
     assert breakdown.loc['gehen']['freq'] == 224
 
 
+def test_breakdown_anchor(germaparl):
+    corpus = get_corpus(germaparl)
+    restricted = corpus.query('[pos="APPR"]@1[pos="ADJA"][pos="NN"]')
+    bd = restricted.breakdown(p_atts=['lemma'], start=1, end=1)
+    assert bd.sort_values(by='freq', ascending=False).index[0] == 'neu'
+
+
 def test_matches(germaparl):
     corpus = get_corpus(germaparl)
     dump = corpus.query('"SPD"')