Merge remote-tracking branch 'upstream/hotfixes' into release

Dockerfile

@@ -13,7 +13,7 @@ RUN apt-get -y install libtool flex bison pkg-config g++ libssl-dev automake
 RUN apt-get -y install libjemalloc-dev libboost-dev libboost-filesystem-dev libboost-system-dev libboost-regex-dev python3-dev autoconf flex bison cmake
 RUN apt-get -y install libxml2-dev libxslt-dev libfreetype6-dev libsuitesparse-dev
 RUN pip install -U wheel six pytest
-RUN pip install colorama==0.4.6 contourpy==1.2.0 cycler==0.12.1 deprecation==2.1.0 fonttools==4.49.0 graphviz==0.20.1 intervaltree==3.1.0 kiwisolver==1.4.5 lxml==5.1.0 matplotlib==3.8.3 networkx==3.2.1 numpy==1.26.4 packaging==23.2 pandas==2.2.1 pillow==10.2.0 pydotplus==2.0.2 pyparsing==3.1.1 python-dateutil==2.9.0.post0 pytz==2024.1 scipy==1.12.0 six==1.16.0 sortedcontainers==2.4.0 StringDist==1.0.9 tqdm==4.66.2 tzdata==2024.1 
+RUN pip install colorama==0.4.6 contourpy==1.2.0 cycler==0.12.1 deprecation==2.1.0 fonttools==4.49.0 graphviz==0.20.1 intervaltree==3.1.0 kiwisolver==1.4.5 lxml==5.1.0 matplotlib==3.8.3 networkx==3.2.1 numpy==1.26.4 packaging==23.2 pandas==2.2.1 pillow==10.2.0 pydotplus==2.0.2 pyparsing==3.1.1 python-dateutil==2.9.0.post0 pytz==2024.1 scipy==1.12.0 six==1.16.0 sortedcontainers==2.4.0 tqdm==4.66.2 tzdata==2024.1
 
 COPY . /app
 RUN cd /app && python setup.py install

pm4py/algo/label_splitting/variants/contextual.py

@@ -20,8 +20,7 @@
 import pandas as pd
 from enum import Enum
 from pm4py.util import constants, xes_constants, exec_utils, pandas_utils, nx_utils
-from pm4py.util import regex
-import stringdist
+from pm4py.util import regex, string_distance
 
 
 class Parameters(Enum):
@@ -56,7 +55,7 @@ def __normalized_edit_distance(s1: str, s2: str) -> float:
     """
     ned = 0
     if len(s1) > 0 or len(s2) > 0:
-        ed = stringdist.levenshtein(s1, s2)
+        ed = string_distance.levenshtein(s1, s2)
         ned = ed / max(len(s1), len(s2))
     return ned
 

pm4py/util/string_distance.py

@@ -15,11 +15,36 @@
     along with PM4Py.  If not, see <https://www.gnu.org/licenses/>.
 '''
 import sys
+import importlib.util
 from typing import List, Union
 
-import stringdist
 
-levenshtein = lambda stru1, stru2: stringdist.levenshtein(stru1, stru2)
+def levenshtein_distance(s1, s2):
+    if len(s1) < len(s2):
+        return levenshtein_distance(s2, s1)
+
+    if len(s2) == 0:
+        return len(s1)
+
+    previous_row = range(len(s2) + 1)
+    for i, c1 in enumerate(s1):
+        current_row = [i + 1]
+        for j, c2 in enumerate(s2):
+            insertions = previous_row[j + 1] + 1
+            deletions = current_row[j] + 1
+            substitutions = previous_row[j] + (c1 != c2)
+            current_row.append(min(insertions, deletions, substitutions))
+        previous_row = current_row
+
+    return previous_row[-1]
+
+
+def levenshtein(stru1, stru2):
+    if importlib.util.find_spec("stringdist"):
+        import stringdist
+        return stringdist.levenshtein(stru1, stru2)
+
+    return levenshtein_distance(stru1, stru2)
 
 
 def argmin_levenshtein(stru: str, list_stri: List[str]) -> Union[str, None]:

requirements.txt

@@ -10,5 +10,4 @@ pandas
 pydotplus
 pytz
 scipy
-stringdist
 tqdm

requirements_complete.txt

@@ -20,6 +20,5 @@ pytz
 scipy
 six
 sortedcontainers
-StringDist
 tqdm
 tzdata

requirements_stable.txt

@@ -20,6 +20,5 @@ pytz==2024.1
 scipy==1.12.0
 six==1.16.0
 sortedcontainers==2.4.0
-StringDist==1.0.9
 tqdm==4.66.2
 tzdata==2024.1

third_party/LICENSES_TRANSITIVE.md

@@ -28,6 +28,5 @@ libraries are added/removed.
 | scipy | https://pypi.org/project/scipy | BSD License | 1.12.0 |
 | six | https://pypi.org/project/six | MIT License (MIT) | 1.16.0 |
 | sortedcontainers | https://pypi.org/project/sortedcontainers | Apache Software License (Apache 2.0) | 2.4.0 |
-| StringDist | https://pypi.org/project/StringDist | MIT License (MIT) | 1.0.9 |
 | tqdm | https://pypi.org/project/tqdm | MIT License, Mozilla Public License 2.0 (MPL 2.0) (MPL-2.0 AND MIT) | 4.66.2 |
 | tzdata | https://pypi.org/project/tzdata | Apache Software License (Apache-2.0) | 2024.1 |