Added gigafida to file creation

.gitignore

@@ -10,3 +10,5 @@ dockerfiles/database/create.js
 *__pycache__/
 env.local
 logs/*
+.idea/
+venv/

Makefile

@@ -24,9 +24,9 @@ SSKJ_JSON = "$(MAKE_ROOT)/data/sskj_senses.json"
 # for pre-generation the index of all headwords and functors
 APPINDEX_PATH = "$(MAKE_ROOT)/data/appindex.json"
 
-OUTPUT = "db"
-# OUTPUT = "file"
-OUTDIR = "/tmp/three"  # if you're running this in docker, make sure to mount the volume
+# OUTPUT = "db"
+OUTPUT = "file"
+OUTDIR = "/project/data"  # if you're running this in docker, make sure to mount the volume
 DBADDR = "0.0.0.0:27017"  # don't use localhost
 
 # credentials from .gitignored file

data/ssj_file_link

@@ -1 +0,0 @@
-/home/kristjan/git/diploma/data/ssj500k-sl.TEI/ssj500k-sl.body.xml

requirements.txt

@@ -0,0 +1,36 @@
+asn1crypto==0.24.0
+Click==7.0
+# corpusparser==0.0.1
+cryptography==2.1.4
+Flask==1.1.1
+Flask-Cors==3.0.8
+Flask-PyMongo==2.3.0
+gunicorn==19.9.0
+idna==2.6
+itsdangerous==1.1.0
+Jinja2==2.10.1
+joblib==0.13.2
+keyring==10.6.0
+keyrings.alt==3.0
+lxml==4.4.0
+MarkupSafe==1.1.1
+numpy==1.17.0
+pandas==0.25.0
+pathlib==1.0.1
+pycrypto==2.6.1
+# pygobject
+pymongo==3.8.0
+python-dateutil==2.8.0
+pytz==2019.2
+pyxdg==0.25
+PyYAML==5.1.2
+scikit-learn==0.21.3
+scipy==1.3.0
+SecretStorage==2.3.1
+# Editable install with no version control (seqparser==0.0.1)
+six==1.11.0
+sklearn==0.0
+# Editable install with no version control (valency==0.1.1)
+
+Werkzeug==0.15.5
+

src/backend_flask/app.py

@@ -37,7 +37,8 @@ app = Flask(__name__)
 app.config.from_object("db_config")
 mongo = PyMongo(app)
 
-app.config["CORPORA"] = ["ssj", "kres"]
+# app.config["CORPORA"] = ["ssj", "kres"]
+app.config["CORPORA"] = ["ssj"]
 app.config["BANNED_HEADWORDS"] = ["biti"]
 app.config["QUERY_LIMIT"] = 1000
 
@@ -452,9 +453,18 @@ def prepare_app_index(appindex_json, sskj_wordlist):
         res_hws = {}
         res_fns = {}
 
+        print('CORPUS...!!...')
+        print(corpus)
+        a = mongo.db[corpus]
+        print('TEST_OK')
+        print(a)
+        print(mongo.db)
+        a = mongo.db.list_collection_names()
+        print('TEST_OK2')
         nentries = mongo.db[corpus].count()
         idx = 0
         for e in mongo.db[corpus].find({}):
+            print('aaa')
             if "headwords" not in e:
                 continue
             for hw in e["headwords"]:

src/pkg/cjvt-corpusparser

@@ -1 +1 @@
-Subproject commit 01adf47b9b63b43f86bff52429792b0de2327ddd
+Subproject commit 2e1d8d06b33eb4e64d3558fea2161811e81f6a28