data path

Author: woodthom2

README.md

@@ -65,7 +65,8 @@ As an alternative to downloading models, you can set environment variables so th
 
 * `HARMONY_CLASSIFIER_ENDPOINT` - this can be an Azure Functions deployment of the text triage spaCy model. Example: https://twspacytest.azurewebsites.net/api/triage
 * `HARMONY_NER_ENDPOINT` - this can be an Azure Functions deployment of the NER spaCy model. Example: https://twspacytest.azurewebsites.net/api/ner
-* `HARMONY_DATA_PATH` - determines where model files are stored. Defaults to `HOME DIRECTORY/harmony`
+* `HARMONY_SPACY_PATH` - determines where model files are stored. Defaults to `HOME DIRECTORY/harmony`
+* `HARMONY_DATA_PATH` - determines where data files are stored. Defaults to `HOME DIRECTORY/harmony`
 * `HARMONY_NO_PARSING` - set to 1 to import a lightweight variant of Harmony which doesn't support PDF parsing.
 * `HARMONY_NO_MATCHING` - set to 1 to import a lightweight variant of Harmony which doesn't support matching.
 

src/harmony/parsing/text_extraction/ensemble_named_entity_recogniser.py

@@ -24,7 +24,7 @@
 def load_spacy_models():
     if spacy_models["ner"]  is None:
         if os.environ.get("HARMONY_NER_ENDPOINT") is None or os.environ.get("HARMONY_NER_ENDPOINT") == "":
-            path = os.getenv("HARMONY_DATA_PATH", os.path.expanduser("~") + "/harmony") + '/harmony_spacy_models/11_ner_0_spacy/model-best'
+            path = os.getenv("HARMONY_SPACY_PATH", os.path.expanduser("~") + "/harmony") + '/harmony_spacy_models/11_ner_0_spacy/model-best'
             if not os.path.isdir(path):
                 print(f"Could not find model at {path}")
                 print("Please run:\nfrom harmony import download_models\ndownload_models()")
@@ -33,7 +33,7 @@ def load_spacy_models():
 
     if spacy_models["classifier"] is None:
         if os.environ.get("HARMONY_CLASSIFIER_ENDPOINT") is None or os.environ.get("HARMONY_CLASSIFIER_ENDPOINT") == "":
-            path = os.getenv("HARMONY_DATA_PATH", os.path.expanduser("~") + "/harmony") + '/harmony_spacy_models/29_classifier_spacy/model-best'
+            path = os.getenv("HARMONY_SPACY_PATH", os.path.expanduser("~") + "/harmony") + '/harmony_spacy_models/29_classifier_spacy/model-best'
             if not os.path.isdir(path):
                 print(f"Could not find model at {path}")
                 print ("Please run:\nfrom harmony import download_models\ndownload_models()")

src/harmony/util/model_downloader.py

@@ -13,10 +13,10 @@ def download_models(is_force=False):
     """
     Downloads spaCy models to local.
     """
-    local_path = os.getenv("HARMONY_DATA_PATH", os.path.expanduser("~") + "/harmony")
+    local_path = os.getenv("HARMONY_SPACY_PATH", os.path.expanduser("~") + "/harmony")
 
     print(
-        "Downloading spaCy models to " + local_path + ".\nSet environment variable HARMONY_DATA_PATH if you want to change model file location.")
+        "Downloading spaCy models to " + local_path + ".\nSet environment variable HARMONY_SPACY_PATH if you want to change model file location.")
 
     # Base URL of the model files in Azure Blob Storage static hosted site.
     url = "https://harmonyapistorage.z33.web.core.windows.net/harmony_spacy_models.tar.bz2"
@@ -57,4 +57,4 @@ def download_models(is_force=False):
     is_force = False
     if len(sys.argv) > 1 and "force" in sys.argv[1]:
         is_force = True
-    download_models(is_force)
+    download_models(is_force)