correctly catch errors thrown from Java in the Coma algorithm, raised…

… in #58 (#69)
delftdata · Nov 9, 2023 · 057aec8 · 057aec8
1 parent 3f8a9e5
commit 057aec8
Show file tree

Hide file tree

Showing 2 changed files with 20 additions and 12 deletions.
diff --git a/README.md b/README.md
@@ -34,10 +34,11 @@ Valentine can be used to find matches among columns of a given pair of pandas Da
 ### Matching methods
 In order to do so, the user can choose one of the following 5 matching methods:
 
-1.   `Coma(int: max_n str: strategy)` is a python wrapper around [COMA 3.0 Comunity edition](https://sourceforge.net/projects/coma-ce/)
+1.   `Coma(int: max_n, bool: use_instances, str: java_xmx)` is a python wrapper around [COMA 3.0 Comunity edition](https://sourceforge.net/projects/coma-ce/)
      *    **Parameters**: 
-           *    **max_n**(*int*) - Accept similarity threshold, default is 0.
-           *    **strategy**(*str*) - Choice of "COMA\_OPT" (schema based matching - default) or "COMA\_OPT\_INST" (schema and instance based matching)
+           *    **max_n**(*int*) - Accept similarity threshold, (default: 0).
+           *    **use_instances**(*bool*) - Wheather Coma will make use of the data instances or just the schema information, (default: False).
+           *    **java_xmx**(*str*) - The amount of RAM that Coma is allowed to use, (default: "1024m") .
 
 2.   `Cupid(float: w_struct, float: leaf_w_struct, float: th_accept)` is the python implementation of the paper [Generic Schema Matching with Cupid](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.79.4079&rep=rep1&type=pdf)
      *    **Parameters**:

diff --git a/valentine/algorithms/coma/coma.py b/valentine/algorithms/coma/coma.py
@@ -10,6 +10,10 @@
 from ...utils.utils import get_project_root
 
 
+class JavaException(Exception):
+    pass
+
+
 class Coma(BaseMatcher):
 
     def __init__(self,
@@ -45,15 +49,18 @@ def __run_coma_jar(self,
         source_data = os.path.join(tmp_folder_path, source_table_f_name)
         target_data = os.path.join(tmp_folder_path, target_table_f_name)
         coma_output_path = os.path.join(tmp_folder_path, coma_output_path)
-        with open(os.path.join(tmp_folder_path, "NUL"), "w") as fh:
-            subprocess.call(['java', f'-Xmx{self.__java_XmX}',
-                             '-cp', jar_path,
-                             '-DinputFile1=' + source_data,
-                             '-DinputFile2=' + target_data,
-                             '-DoutputFile=' + coma_output_path,
-                             '-DmaxN=' + str(self.__max_n),
-                             '-Dstrategy=' + self.__strategy,
-                             'Main'], stdout=fh, stderr=fh)
+        try:
+            subprocess.check_output(['java', f'-Xmx{self.__java_XmX}',
+                                     '-cp', jar_path,
+                                     '-DinputFile1=' + source_data,
+                                     '-DinputFile2=' + target_data,
+                                     '-DoutputFile=' + coma_output_path,
+                                     '-DmaxN=' + str(self.__max_n),
+                                     '-Dstrategy=' + self.__strategy,
+                                     'Main'], stderr=subprocess.DEVNULL)
+        except subprocess.CalledProcessError:
+            raise JavaException("Either Java (JRE) is not installed or Java does not have enough memory to operate. "
+                                "Try raising the java_xmx parameter of the Coma class")
 
     def __write_schema_csv_files(self,
                                  table1: BaseTable,