Better elastic search

confs/config.py

@@ -4,6 +4,7 @@
 User configuration
 """
 
+import sys
 import os
 import re
 import argparse
@@ -18,29 +19,33 @@
 
 #############################
 # Command line arguments
-
-def my_cli_arguments():
-    arg = argparse.ArgumentParser(description='REST API server based on Flask')
-    arg.add_argument("--no-security", action="store_false", dest='security',
-                     help='force removal of login authentication on resources')
-    arg.add_argument("--debug", action="store_true", dest='debug',
-                     help='enable debugging mode')
-    arg.add_argument(
-        "--remove-old", action="store_true", dest='rm',
-        help='force removal of previous new tables')
-    arg.set_defaults(security=True, debug=False)
-    return arg.parse_args()
-
 args = None
 default_debug = False
-is_gunicorn = "gunicorn" in os.environ.get("SERVER_SOFTWARE", "")
-
-if not is_gunicorn:
-    args = my_cli_arguments()
-    default_debug = args.debug
+if 'operations.py' not in sys.argv[0]:
+
+    def my_cli_arguments():
+        arg = argparse.ArgumentParser(
+            description='REST API server based on Flask')
+        arg.add_argument(
+            "--no-security", action="store_false", dest='security',
+            help='force removal of login authentication on resources')
+        arg.add_argument(
+            "--debug", action="store_true", dest='debug',
+            help='enable debugging mode')
+        arg.add_argument(
+            "--remove-old", action="store_true", dest='rm',
+            help='force removal of previous new tables')
+        arg.set_defaults(security=True, debug=False)
+        return arg.parse_args()
+
+    is_gunicorn = "gunicorn" in os.environ.get("SERVER_SOFTWARE", "")
+
+    if not is_gunicorn:
+        args = my_cli_arguments()
+        default_debug = args.debug
 
 DEBUG = os.environ.get('API_DEBUG', default_debug)
-#DEBUG = True
+# DEBUG = True
 
 ###################################################
 ###################################################

operations.py

@@ -5,10 +5,15 @@
 Operations based on services pre-installed
 """
 
+import sys
 from operations import rethink2elastic as r2e
 from operations import rethink
-# from restapi import get_logger
-# logger = get_logger(__name__)
+from restapi import get_logger
+log = get_logger(__name__)
+
+skip_lexique = True
+if len(sys.argv) > 1:
+    skip_lexique = bool(int(sys.argv[1]))
 
 #########################
 # RETHINKDB
@@ -19,10 +24,13 @@
 # rethink.build_zoom(force=False)
 # rethink.medium_expo_thumbnail(force=False)
 # rethink.fix_languages()
-# rethink.some_operation()
+rethink.some_operation()
+# rethink.find_word(['sucre', 'atlas', 'nympha'])
+# exit(1)
 
 #########################
 # RETHINKDB 2 ELASTICSEARCH
+log.info("Skipping Lexique creation? %s", skip_lexique)
 
 # r2e.make()
 # FIXME

operations/rethink.py

@@ -55,7 +55,7 @@
 
 ######################
 # Parameters
-if args.rm:
+if args is not None and args.rm:
     log.info("Remove previous data")
     tables = query.list_tables()
     if tin in tables:
@@ -94,6 +94,32 @@ def convert_schema():
     # check_indexes(t2in)
 
 
+def find_word(tofind=[]):
+
+    def find(words):
+        for word in tofind:
+            if word in words.lower():
+                log.info("ID: %s has %s", element.get('record'), word)
+                return True
+        return False
+
+    table = query.get_table_query('datadocs')
+
+    for element in table.run():
+        try:
+            image = element.get('images', []).pop()
+        except IndexError:
+            continue
+        # pp(image)
+
+        texts = image.get('transcriptions', [])
+        texts.extend(list(image.get('translations', {}).values()))
+        for words in texts:
+            if words is not None:
+                if find(words):
+                    break
+
+
 def some_operation():
 
     # x = "48167161-d5ce-4ed0-afef-cb2a710eab17"