Merge pull request #11 from xgaia/dev

Version 0.4: Bed files

README.md

@@ -14,10 +14,10 @@ Installation
 
 Clone the repository
 
-    git clone https://github.com/askomics/asko-cli.git
-    cd asko-cli
+    git clone https://github.com/askomics/askocli.git
+    cd askocli
 
-Set up a virtual environment:
+Set up and activate a virtual environment:
 
     python3 -m venv venv
     source venv/bin/activate
@@ -31,7 +31,6 @@ Usage example
 
 Integration
 
-    askocli integrate -a http://localhost -p 6543 -k mYap1Key path/to/file.csv
     askocli integrate -a http://localhost -p 6543 -k mYap1Key path/to/file.csv
     askocli integrate -a http://localhost -p 6543 -k mYap1Key -e gene transcript -t Arabidopsis_thaliana path/to/file.gff
     askocli integrate -a http://localhost -p 6543 -k mYap1Key path/to/file.ttl
@@ -54,3 +53,7 @@ History
    - Option `--disabled-columns` to don't integrate a columns of a TSV
 - 0.3.2
    - FIX error message
+- 0.4: Bed files integration
+	- Integration of Bed files
+	- Option `--uri` to specify an uri for the entity
+	- Option `--headers` to set custom headers for TSV files

libaskocli/__init__.py

@@ -6,6 +6,7 @@
 from os.path import basename
 import json
 import requests
+import csv
 # import logging
 
 # logging.getLogger('requests').setLevel(logging.CRITICAL)
@@ -47,6 +48,7 @@ def __init__(self, url, apikey, file_type):
         self.type = file_type
         self.public = False
         self.disabled_columns = []
+        self.csv_headers = []
 
     def set_cookie(self):
         """set the session cookie of user
@@ -172,27 +174,53 @@ def guess_col_types(self):
         self.col_types = json.loads(response.text)['types']
         self.col_types[0] = 'entity_start'
 
+    def set_headers(self, headers):
+        """Set the headers of the CSV file"""
 
-    def integrate_data(self):
+        if headers is not None:
+            self.csv_headers = headers
+            return
+
+        headers = []
+        with open(self.path, 'r', encoding="utf-8", errors="ignore") as tabfile:
+
+            # Get dialect
+            contents = tabfile.readline()
+            dialect = csv.Sniffer().sniff(contents, delimiters=';,\t ')
+            tabfile.seek(0)
+
+            # Load the file with reader
+            tabreader = csv.reader(tabfile, dialect=dialect)
+
+            # first line is header
+            headers = next(tabreader)
+            headers = [h.strip() for h in headers]
+
+        self.csv_headers = headers
+
+
+    def integrate_data(self, uri):
         """Integrate the csv file into the triplestore
 
         :returns: response text
         :rtype: string
         """
 
-
         url = self.url + '/load_data_into_graph'
 
-
         json_dict = {
             'file_name': basename(self.path),
             'col_types': self.col_types,
             'disabled_columns': self.disabled_columns,
             'key_columns': self.key_columns,
             'public': self.public,
-            'forced_type': self.type
+            'forced_type': self.type,
+            'headers': self.csv_headers
         }
 
+        if uri is not None:
+            json_dict['uri'] = uri
+
         response = requests.post(url, cookies=self.cookies, headers=self.headers, json=json_dict)
 
         if response.status_code != 200:
@@ -204,13 +232,14 @@ def integrate_data(self):
 
         return response.text
 
-    def integrate_gff(self, taxon, entities):
+    def integrate_gff(self, taxon, entities, uri):
         """Integrate a gff into the triplestore
 
         :param taxon: taxon
         :type taxon: string
         :param entities: list of entities to integrate
         :type entities: list
+        :param uri: a custom URI for this entity
         :returns: response text
         :rtype: string
         """
@@ -225,6 +254,9 @@ def integrate_gff(self, taxon, entities):
             'forced_type': self.type
         }
 
+        if uri is not None:
+            json_dict['uri'] = uri
+
         response = requests.post(url, cookies=self.cookies, headers=self.headers, json=json_dict)
 
         if response.status_code != 200:
@@ -236,6 +268,47 @@ def integrate_gff(self, taxon, entities):
 
         return response.text
 
+    def integrate_bed(self, entity_name, taxon, uri):
+        """Integrate a bed file into AskOmics
+
+        :param entity_name: The entityname, descibed in the bed file
+        :type entity_name: string
+        :param taxon: the taxon described into the bed file
+        :type taxon: string
+        :param uri: a custom URI for this entity
+        :type uri: string
+        :returns: response text
+        :rtype: string
+        """
+
+        url = self.url + '/load_bed_into_graph'
+
+        if taxon is None:
+            taxon = ''
+        if entity_name is None:
+            entity_name = ''
+
+        json_dict = {
+            'file_name': basename(self.path),
+            'taxon': taxon,
+            'entity_name': entity_name,
+            'public': self.public
+        }
+
+        if uri is not None:
+            json_dict['uri'] = uri
+
+        response = requests.post(url, cookies=self.cookies, headers=self.headers, json=json_dict)
+
+        if response.status_code != 200:
+            raise Exception('Unexpected response from AskOmics when integrate bed: ' +
+                            str(response.status_code) + '\n' + response.text)
+
+        if 'error' in json.loads(response.text):
+            raise Exception('AskOmics error: ' + str(json.loads(response.text)['error']))
+
+        return response.text
+
     def integrate_ttl(self):
         """Integrate a ttl into the triplestore
 

libaskocli/actions/integrate.py

@@ -18,18 +18,28 @@ def run(self, args):
         :type args: Namespace
         """
 
-        parser = argparse.ArgumentParser(prog='askocli ' + self.__class__.__name__, description='Integrate data to a distant AskOmics')
+        parser = argparse.ArgumentParser(prog='askocli integrate', description='Integrate data to a distant AskOmics')
         askomics_auth(parser)
         askomics_url(parser)
         parser.add_argument('file', nargs='?', type=str, action="store", help="file to integrate")
         parser.add_argument('--file-type', help='The file type')
         parser.add_argument('--public', action='store_true')
+        parser.add_argument('--uri', help='Custom URI')
 
-        parser.add_argument('--key-columns', nargs='*', help='List of the key columns index')
-        parser.add_argument('--disabled-columns', nargs='*', help='List of columns index to disable')
-        parser.add_argument('-c', '--columns', nargs='*', help='List of forced columns types')
-        parser.add_argument('-e', '--entities', nargs='*', help='List of entities to integrate')
-        parser.add_argument('-t', '--taxon', help='Taxon')
+        # CSV args
+        parser.add_argument('--headers', nargs='*', help='List of custom headers  (csv)')
+        parser.add_argument('--key-columns', nargs='*', help='List of the key columns index  (csv)')
+        parser.add_argument('--disabled-columns', nargs='*', help='List of columns index to disable  (csv)')
+        parser.add_argument('-c', '--columns', nargs='*', help='List of forced columns types  (csv)')
+
+        # GFF args
+        parser.add_argument('-e', '--entities', nargs='*', help='List of entities to integrate  (gff)')
+
+        # GFF and BED args
+        parser.add_argument('-t', '--taxon', help='Taxon  (gff and bed)')
+
+        # BED args
+        parser.add_argument('-n', '--entity-name', help='Entity name  (bed)')
 
         args = parser.parse_args(args)
 
@@ -48,9 +58,11 @@ def run(self, args):
         ext = os.path.splitext(basename(args.file))[1].lower()
 
         if ext in ('.gff', '.gff2', '.gff3') or args.file_type == 'gff':
-            api.integrate_gff(args.taxon, args.entities)
+            api.integrate_gff(args.taxon, args.entities, args.uri)
         elif ext == '.ttl' or args.file_type == 'ttl':
             api.integrate_ttl()
+        elif ext in ('.bed',) or args.file_type == 'bed':
+            api.integrate_bed(args.entity_name, args.taxon, args.uri)
         else:
             if args.key_columns:
                 api.set_key_columns(args.key_columns)
@@ -60,4 +72,5 @@ def run(self, args):
                 api.guess_col_types()
             if args.disabled_columns:
                 api.set_disabled_columns(args.disabled_columns)
-            api.integrate_data()
+            api.set_headers(args.headers)
+            api.integrate_data(args.uri)

setup.py

@@ -3,12 +3,12 @@
 
 setup(
     name='askocli',
-    version='0.3.4',
+    version='0.4',
     description='Command line interface for a distant AskOmics',
     author='Xavier Garnier',
     author_email='[email protected]',
     url='https://github.com/askomics/askocli',
-    download_url='https://github.com/askomics/askocli/archive/0.3.4.git tar.gz',
+    download_url='https://github.com/askomics/askocli/archive/0.4.git tar.gz',
     install_requires=['requests>=2.4.3'],
     packages=find_packages(),
     license='AGPL',