commit 19b0e2a10258e57b1f909d094f0b53f9495644fb
Author: vivekvardhanadepu <vivekvicky839@gmail.com>
Date:   Mon May 24 20:48:43 2021 +0530

    check_config added

diff --git a/README.md b/README.md
index 7984ab5..0550221 100644
--- a/README.md
+++ b/README.md
@@ -4,7 +4,7 @@ The procedure for lexical selection training is a bit messy, with various script
 
 for more, read https://wiki.apertium.org/wiki/Ideas_for_Google_Summer_of_Code/User-friendly_lexical_selection_training
 
-## coding challenges
+## coding challenges *(using for testing)*
 
 In directory coding_challenges,
 
diff --git a/check_config.py b/check_config.py
new file mode 100644
index 0000000..864d000
--- /dev/null
+++ b/check_config.py
@@ -0,0 +1,40 @@
+# parses the config, check if the tools are present
+
+from tomlkit import parse, dumps
+import os
+
+# urls of the required tools and data
+corpora_url = ""
+lex_tools_url = ""
+fast_align_url = ""
+langs_url = ""
+
+def parse_config(filename='config.toml'):
+    with open(filename) as config_file:
+        config_toml = config_file.read()
+        config = parse(config_toml)
+
+    # gives error if not parsed well
+    assert config_toml == dumps(config)
+
+    if not os.path.isfile(config['CORPUS_SL']):
+        print(config['CORPUS_SL'], "is not a file. Provide a valid file or to download,\n look", corpora_url)
+
+    if not os.path.isfile(config['CORPUS_TL']):
+        print(config['CORPUS_TL'], "is not a file. Provide a valid file or to download,\n look", corpora_url)
+
+    if not os.path.isdir(config['LEX_TOOLS']):
+        print(config['LEX_TOOLS'], "is not a directory. Provide a valid directory or to install,\n follow", lex_tools_url)
+
+    if not os.path.isdir(config['FAST_ALIGN']):
+        print(config['FAST_ALIGN'], "is not a directory. Provide a valid directory or to install,\n follow", fast_align_url)
+
+    if not os.path.isdir(config['LANG_DATA']):
+        print(config['LANG_DATA'], "is not a directory. Provide a valid directory or to install,\n follow", langs_url)
+
+    
+    
+    return config
+
+if __name__ == '__main__':
+    parse_config()
\ No newline at end of file
diff --git a/config.toml b/config.toml
index 9ba35b5..8809d38 100644
--- a/config.toml
+++ b/config.toml
@@ -1,25 +1,26 @@
 # configuration for lexical training
+# Note: pass absolute paths
 
 # corpus name
-CORPUS = 
+CORPUS = "europarl-v7"
 
 # source language
-SL = 
+SL = "eng"
 
 # target language
-TL = 
+TL = "spa"
 
 # source corpus
-CORPUS_SL = 
+CORPUS_SL = "europarl-v7.eng-spa.eng"
 
 # target corpus
-CORPUS_TL = 
+CORPUS_TL = "europarl-v7.eng-spa.spa"
 
 # apertium-lex-tools scripts
-LEX_TOOLS = 
+LEX_TOOLS = "/home/vivek/Documents/FOSS/apertium/apertium-lex-tools/scripts"
 
 # apertium language data
-DATA = 
+LANG_DATA = "/home/vivek/Documents/FOSS/apertium/user-friendly-lexical-training/coding_challenges/apertium-eng-spa"
 
 # fast align build folder
-FAST_ALIGN = 
\ No newline at end of file
+FAST_ALIGN = "/home/vivek/Documents/FOSS/apertium/user-friendly-lexical-training/coding_challenges/fast_align/build"
\ No newline at end of file
diff --git a/config_parser.py b/config_parser.py
deleted file mode 100644
index fb544d8..0000000
--- a/config_parser.py
+++ /dev/null
@@ -1,14 +0,0 @@
-from tomlkit import parse, dumps
-
-def parse_config(filename='config.toml'):
-    with open(filename) as config_file:
-        config_toml = config_file.read()
-        config = parse(config_toml)
-
-    # gives error if not parsed well
-    assert config_toml == dumps(config)
-    
-    return config
-
-if __name__ == '__main__':
-    parse_config()
\ No newline at end of file
diff --git a/lexical_training.log b/lexical_training.log
index e69de29..2356a59 100644
--- a/lexical_training.log
+++ b/lexical_training.log
@@ -0,0 +1 @@
+{'CORPUS': 'europarl-v7', 'SL': 'eng', 'TL': 'spa', 'CORPUS_SL': 'europarl-v7.eng-spa.eng', 'CORPUS_TL': 'europarl-v7.eng-spa.spa', 'LEX_TOOLS': '/home/vivek/Documents/FOSS/apertium/apertium-lex-tools/scripts', 'DATA': '/home/vivek/Documents/FOSS/apertium/user-friendly-lexical-training/coding_challenges/apertium-eng-spa', 'FAST_ALIGN': '/home/vivek/Documents/FOSS/apertium/user-friendly-lexical-training/coding_challenges/fast_align/build'}
diff --git a/lexical_training.py b/lexical_training.py
index 1208a96..ace48b3 100644
--- a/lexical_training.py
+++ b/lexical_training.py
@@ -1,9 +1,8 @@
 # lexical training script
-from config_parser import parse_config
+from check_config import parse_config
 
 def main():
     config = parse_config()
-    print(config)
 
 if __name__ == '__main__':
     main()
\ No newline at end of file