Merge pull request #138 from USCDataScience/docs

Added documentation to methods
chrismattmann · Apr 5, 2017 · 4590b23 · 4590b23
2 parents b5bd593 + 716a223
commit 4590b23
Show file tree

Hide file tree

Showing 6 changed files with 313 additions and 26 deletions.
diff --git a/tika/detector.py b/tika/detector.py
@@ -19,10 +19,20 @@
 from .tika import detectType1, callServer, ServerEndpoint
 
 def from_file(filename):
+    '''
+    Detects MIME type of specified file
+    :param filename: file whose type needs to be detected
+    :return: MIME type
+    '''
     jsonOutput = detectType1('type', filename)
     return jsonOutput[1]
 
 def from_buffer(string):
+    '''
+    Detects MIME type of the buffered content
+    :param string: buffered content whose type needs to be detected
+    :return:
+    '''
     status, response = callServer('put', ServerEndpoint, '/detect/stream', string,
                                   {'Accept': 'text/plain'}, False)
     return response
diff --git a/tika/language.py b/tika/language.py
@@ -19,10 +19,20 @@
 from .tika import detectLang1, callServer, ServerEndpoint
 
 def from_file(filename):
+    '''
+    Detects language of the file
+    :param filename: path to file whose language needs to be detected
+    :return:
+    '''
     jsonOutput = detectLang1('file', filename)
     return jsonOutput[1]
 
 def from_buffer(string):
+    '''
+    Detects language of content in the buffer
+    :param string: buffered data
+    :return:
+    '''
     status, response = callServer('put', ServerEndpoint, '/language/string', string,
                                   {'Accept': 'text/plain'}, False)
     return response
diff --git a/tika/parser.py b/tika/parser.py
@@ -21,6 +21,15 @@
 import json
 
 def from_file(filename, serverEndpoint=ServerEndpoint, xmlContent=False):
+    '''
+    Parses a file for metadata and content
+    :param filename: path to file which needs to be parsed
+    :param serverEndpoint: Server endpoint url
+    :param xmlContent: Whether or not XML content be requested.
+                    Default is 'False', which results in text content.
+    :return: dictionary having 'metadata' and 'content' keys.
+            'content' has a str value and metadata has a dict type value.
+    '''
     if not xmlContent:
         jsonOutput = parse1('all', filename, serverEndpoint)
     else:
@@ -29,16 +38,29 @@ def from_file(filename, serverEndpoint=ServerEndpoint, xmlContent=False):
 
 
 def from_buffer(string, serverEndpoint=ServerEndpoint, xmlContent=False):
+    '''
+    Parses the content from buffer
+    :param string: Buffer value
+    :param serverEndpoint: Server endpoint. This is optional
+    :param xmlContent: Whether or not XML content be requested.
+                    Default is 'False', which results in text content.
+    :return:
+    '''
     if not xmlContent:
         status, response = callServer('put', serverEndpoint, '/rmeta/text', string,
                 {'Accept': 'application/json'}, False)
     else:
         status, response = callServer('put', serverEndpoint, '/rmeta/xml', string,
-                {'Accept': 'application/json'}, False)      
-  
+                {'Accept': 'application/json'}, False)
+
     return _parse((status,response))
 
 def _parse(jsonOutput):
+    '''
+    Parses JSON response from Tika REST API server
+    :param jsonOutput: JSON output from Tika Server
+    :return: a dictionary having 'metadata' and 'content' values
+    '''
     parsed={}
     if not jsonOutput:
         return parsed
@@ -62,7 +84,7 @@ def _parse(jsonOutput):
             if n != "X-TIKA:content":
                 if n in parsed["metadata"]:
                     if not isinstance(parsed["metadata"][n], list):
-                        parsed["metadata"][n] = [parsed["metadata"][n]]                    
+                        parsed["metadata"][n] = [parsed["metadata"][n]]
                     parsed["metadata"][n].append(js[n])
                 else:
                     parsed["metadata"][n] = js[n]