Merge branch 'main' of https://github.com/brightway-lca/brightway2-io

.github/workflows/github_action_trigger_submodule_pull_reusable.yml → .github/workflows/trigger_submodule_update_reuse.yml

@@ -1,5 +1,6 @@
-# this workflow re-uses the workflow 'github_action_trigger_submodule_pull_main.yml' in the brightway-documentation repository
-name: Create Workflow Dispatch (Trigger Submodule Pull), Re-Use Workflow
+# This workflow re-uses the workflow 'trigger_submodule_update_main.yml'
+# from the brightway-documentation repository.
+name: Re-Use Workflow - Create Workflow Dispatch (Trigger Submodule Update)
 
 on:
   push:
@@ -10,5 +11,5 @@ on:
 jobs:
     re-use_workflow:
       uses:
-        brightway-lca/brightway-documentation/.github/workflows/github_action_trigger_submodule_pull_main.yml@main
-      secrets: inherit # https://docs.github.com/en/actions/using-workflows/reusing-workflows#passing-secrets-to-nested-workflows
+        brightway-lca/brightway-documentation/.github/workflows/trigger_submodule_update_main.yml@main
+      secrets: inherit # https://docs.github.com/en/actions/using-workflows/reusing-workflows#passing-secrets-to-nested-workflows

bw2io/extractors/csv.py

@@ -17,7 +17,7 @@ class CSVExtractor(object):
     """
 
     @classmethod
-    def extract(cls, filepath, encoding="utf-8-sig"):
+    def extract(cls, filepath, encoding="utf-8-sig", **kwargs):
         """
         Extracts CSV file data from the filepath.
 
@@ -47,4 +47,4 @@ def extract(cls, filepath, encoding="utf-8-sig"):
         with open(filepath, encoding=encoding) as f:
             reader = csv.reader(f)
             data = [row for row in reader]
-        return [os.path.basename(filepath), data]
+        return [os.path.basename(filepath), data]

bw2io/extractors/ecospold1_lcia.py

@@ -18,7 +18,7 @@ class Ecospold1LCIAExtractor(object):
     """
 
     @classmethod
-    def extract(cls, path):
+    def extract(cls, path, **kwargs):
         """
         Extracts ecospold XML file data.
 

bw2io/extractors/ecospold2.py

@@ -235,13 +235,13 @@ def extract_activity(cls, dirpath, filename, db_name):
                 "Included activities start: ",
                 getattr2(
                     stem.activityDescription.activity, "includedActivitiesStart"
-                ).get("text"),
+                )
             ),
             (
                 "Included activities end: ",
                 getattr2(
                     stem.activityDescription.activity, "includedActivitiesEnd"
-                ).get("text"),
+                )
             ),
             (
                 "Geography: ",
@@ -264,7 +264,7 @@ def extract_activity(cls, dirpath, filename, db_name):
         ]
         comment = "\n".join(
             [
-                (" ".join(x) if isinstance(x, tuple) else x)
+                (" ".join(str(i) for i in x) if isinstance(x, tuple) else x)
                 for x in comments
                 if (x[1] if isinstance(x, tuple) else x)
             ]

bw2io/extractors/excel.py

@@ -79,7 +79,7 @@ class ExcelExtractor:
     >>> data = extractor.extract(filepath)
     """
     @classmethod
-    def extract(cls, filepath: Path):
+    def extract(cls, filepath: Path, **kwargs):
         """
         Extract data from an Excel file.
 

bw2io/extractors/json_ld.py

@@ -22,7 +22,7 @@ class JSONLDExtractor(object):
         Directories to ignore when extracting JSON-LD data.
     """
     @classmethod
-    def extract(cls, filepath, add_filename=True):
+    def extract(cls, filepath, add_filename=True, **kwargs):
         """
         Extracts JSON-LD data from the filepath.
 

bw2io/extractors/simapro_csv.py

@@ -162,7 +162,7 @@ class SimaProCSVExtractor(object):
     """
 
     @classmethod
-    def extract(cls, filepath, delimiter=";", name=None, encoding="cp1252"):
+    def extract(cls, filepath, delimiter=";", name=None, encoding="cp1252", **kwargs):
         """
         Extract data from a SimaPro export file (.csv) and returns a list of datasets, global parameters, and project metadata.
 

bw2io/extractors/simapro_lcia_csv.py

@@ -54,7 +54,7 @@ class SimaProLCIACSVExtractor(object):
     """
 
     @classmethod
-    def extract(cls, filepath, delimiter=";", encoding="cp1252"):
+    def extract(cls, filepath, delimiter=";", encoding="cp1252", **kwargs):
         assert os.path.exists(filepath), "Can't find file %s" % filepath
         log, logfile = get_io_logger("SimaPro-LCIA-extractor")
 

bw2io/strategies/lcia.py

@@ -303,7 +303,7 @@ def add_subcategories(obj, mapping):
             )
 
     for method in data:
-        already_have = {(obj["name"], obj["categories"]) for obj in method["exchanges"]}
+        already_have = {(obj["name"], tuple(obj["categories"])) for obj in method["exchanges"]}
 
         new_cfs = []
         for obj in method["exchanges"]:
@@ -313,7 +313,7 @@ def add_subcategories(obj, mapping):
             subcat_cfs = [
                 x
                 for x in add_subcategories(obj, mapping)
-                if (x["name"], x["categories"]) not in already_have
+                if (x["name"], tuple(x["categories"])) not in already_have
             ]
             if subcat_cfs and remove and not obj.get("input"):
                 obj["remove_me"] = True

tests/ecospold2/ecospold2_extractor.py

@@ -12,7 +12,7 @@ def test_extraction_without_synonyms():
         "ei",
     )
     expected = {
-        "comment": "Things and stuff and whatnot\nTechnology:  typical technology for ze Germans!",
+        "comment": "Things and stuff and whatnot\nIncluded activities start:  Includes start stuff\nIncluded activities end:  Includes end stuff\nTechnology:  typical technology for ze Germans!",
         "classifications": [
             ("EcoSpold01Categories", "construction materials/concrete"),
             (
@@ -80,7 +80,7 @@ def test_extraction_without_synonyms():
                 "flow": "075e433b-4be4-448e-9510-9a5029c1ce94",
                 "type": "biosphere",
                 "chemical formula": "h2o2",
-                'formula': 'does_it_hurt_when_dropped_on_foot * 2',
+                "formula": "does_it_hurt_when_dropped_on_foot * 2",
                 "variable name": "it_is_boring_to_do_this_manually",
                 "name": "Water",
                 "classifications": {"CPC": []},
@@ -148,7 +148,7 @@ def test_extraction_with_synonyms():
         "ei",
     )
     expected = {
-        "comment": "Things and stuff and whatnot\nTechnology:  typical technology for ze Germans!",
+        "comment": "Things and stuff and whatnot\nIncluded activities end:  Includes some stuff\nTechnology:  typical technology for ze Germans!",
         "classifications": [
             ("EcoSpold01Categories", "construction materials/concrete"),
             (

tests/fixtures/ecospold2/00000_11111111-2222-3333-4444-555555555555_66666666-7777-8888-9999-000000000000.spold

@@ -4,8 +4,8 @@
     <activityDescription>
       <activity id="c40e3c0a-292f-45a5-88cd-ed18265cb7d7" activityNameId="06ffc039-f73b-440c-a5a0-8dc7393a5e71" parentActivityId="0fcbe58d-60b6-46d9-86bf-183d14732a4d" inheritanceDepth="-1" type="1" specialActivityType="0" energyValues="0">
         <activityName xml:lang="en">concrete block production</activityName>
-        <includedActivitiesStart xml:lang="en" />
-        <includedActivitiesEnd xml:lang="en">Includes some stuff</includedActivitiesEnd>
+        <includedActivitiesStart xml:lang="en">Includes start stuff</includedActivitiesStart>
+        <includedActivitiesEnd xml:lang="en">Includes end stuff</includedActivitiesEnd>
         <generalComment>
           <text xml:lang="en" index="1">Things and stuff and whatnot</text>
         </generalComment>

tests/strategies/lcia.py

@@ -459,6 +459,21 @@ def test_match_subcategories_makes_copies(self):
             self.assertEqual(cf["amount"], 2)
 
 
+def test_categories_as_list():
+    """ issues/212
+    """
+    data = [
+        {
+            "name": "Method 1",
+            "exchanges": [
+                {"categories": ["air",], "name": "Emission", "unit": "kg", "amount": 1.0},
+            ],
+        }
+    ]
+    biosphere_db_name = "example_biosphere"
+    match_subcategories(data, biosphere_db_name) # should pass without traceback
+
+
 def test_rationalize_method_names_no_remove_lt():
     given = [
         {"name": ("aw/o LT", "b", "c w/o LT")},