@@ -1,51 +1,28 @@

-import io

 import re

-import urllib.request

-import urllib.parse

-import xml.etree.ElementTree as ET

-

+from mediawiki import get_wikipage_text

 def get_ancestor(title, language_code, ancestor_language_code):

     """Get and parse the descendant section from en.wiktionary.org for a specific title (usually word)"""

-    request_parameters = {

-        "action": "query",

-        "format": "xml",

-        "export": 1,

-        "exportnowrap": 1,

-        "titles": title,

-        "redirects": 1

-    }

-    request_data = urllib.parse.urlencode(request_parameters)

-    request_data = request_data.encode('utf8')

-    wikipage_request = urllib.request.Request("https://en.wiktionary.org/w/api.php/", request_data)

-    with urllib.request.urlopen(wikipage_request) as wikipage_response:

-        # with open("Wiktionary-20170813141826.xml", "r", encoding="utf-8") as wikipage_response:

-        wikipage_string = wikipage_response.read()

-        root = ET.fromstring(wikipage_string)

-        ns = {"mwns": "http://www.mediawiki.org/xml/export-0.10/"}

-        # wikipage_text_string = root.find("./mwns:page/mwns:title", ns).text

-        wikipage_text_string = root.find("./mwns:page/mwns:revision/mwns:text", ns).text

-        # ET.dump(root)

-        # print(wikipage_text_string)

-        match = re.search(r"\=+Etymology.*?\=+", wikipage_text_string)

-        etymology_string = wikipage_text_string[match.end():-1]

-        ancestor_words = []

-        # {{l|ang|hungor}} start_tag = "{{" end_tag = "}}" parameter_tag = "|"

-        matches = re.findall(r"(?<={{).*?(?=}})",

-                             etymology_string)  # find all matches for every string between {{ and }} in a non-greedy manner

-        for id, match in enumerate(matches):

-            parameters = match.split("|")

-            # {{etyl|gem-pro|en}} {{m|gem-pro|*sagô}}

-            if (parameters[0] == "etyl") and (parameters[1] == ancestor_language_code) and (parameters[2] == language_code):

-                if id < len(matches):

-                    next_match = matches[id + 1]

-                    nm_parameters = next_match.split("|")

-                    if (nm_parameters[0] == "m") and (nm_parameters[1] == ancestor_language_code):

-                        ancestor_words.append({"language": nm_parameters[1], "lemma": nm_parameters[2]})

-            # {{inh|en|gem-pro|*hwītaz}}

-            if (parameters[0] == "inh") and (parameters[1] == language_code) and (parameters[2] == ancestor_language_code):

-                ancestor_words.append({"language": parameters[2], "lemma": parameters[3]})

-            # {{der|it|la|alacer||lively; happy, cheerful}}

-            if (parameters[0] == "der") and (parameters[1] == language_code) and (parameters[2] == ancestor_language_code):

-                ancestor_words.append({"language": parameters[2], "lemma": parameters[3]})

-        return ancestor_words

+    wikipage_text_string = get_wikipage_text(title)

+    match = re.search(r"\=+Etymology.*?\=+", wikipage_text_string)

+    etymology_string = wikipage_text_string[match.end():-1]

+    ancestor_words = []

+    # {{l|ang|hungor}} start_tag = "{{" end_tag = "}}" parameter_tag = "|"

+    matches = re.findall(r"(?<={{).*?(?=}})",

+                         etymology_string)  # find all matches for every string between {{ and }} in a non-greedy manner

+    for id, match in enumerate(matches):

+        parameters = match.split("|")

+        # {{etyl|gem-pro|en}} {{m|gem-pro|*sagô}}

+        if (parameters[0] == "etyl") and (parameters[1] == ancestor_language_code) and (parameters[2] == language_code):

+            if id < len(matches):

+                next_match = matches[id + 1]

+                nm_parameters = next_match.split("|")

+                if (nm_parameters[0] == "m") and (nm_parameters[1] == ancestor_language_code):

+                    ancestor_words.append({"language": nm_parameters[1], "lemma": nm_parameters[2]})

+        # {{inh|en|gem-pro|*hwītaz}}

+        if (parameters[0] == "inh") and (parameters[1] == language_code) and (parameters[2] == ancestor_language_code):

+            ancestor_words.append({"language": parameters[2], "lemma": parameters[3]})

+        # {{der|it|la|alacer||lively; happy, cheerful}}

+        if (parameters[0] == "der") and (parameters[1] == language_code) and (parameters[2] == ancestor_language_code):

+            ancestor_words.append({"language": parameters[2], "lemma": parameters[3]})

+    return ancestor_words

@@ -1,48 +1,27 @@

 __author__ = 'Ray'

-import sys

 import io

 import re

-import urllib.request

-import urllib.parse

-import xml.etree.ElementTree as ET

-

+from mediawiki import get_wikipage_text

 def get_descendants(title):

     """Get and parse the descendant section from en.wiktionary.org for a specific title (usually word)"""

-    request_parameters = {

-        "action": "query",

-        "format": "xml",

-        "export": 1,

-        "exportnowrap": 1,

-        "titles": title,

-        "redirects": 1

-    }

-    request_data = urllib.parse.urlencode(request_parameters)

-    request_data = request_data.encode('utf8')

-    wikipage_request = urllib.request.Request("https://en.wiktionary.org/w/api.php/", request_data)

-    with urllib.request.urlopen(wikipage_request) as wikipage_response:

-        # with open("Wiktionary-20170813141826.xml", "r", encoding="utf-8") as wikipage_response:

-        wikipage_string = wikipage_response.read()

-        root = ET.fromstring(wikipage_string)

-        ns = {"mwns": "http://www.mediawiki.org/xml/export-0.10/"}

-        # wikipage_text_string = root.find("./mwns:page/mwns:title", ns).text

-        wikipage_text_string = root.find("./mwns:page/mwns:revision/mwns:text", ns).text

-        # ET.dump(root)

-        # print(wikipage_text_string)

-        match = re.search(r"\=+Descendants\=+", wikipage_text_string)

-        descendants_string = wikipage_text_string[match.end():-1]

-        descendant_words = []

-        # {{l|ang|hungor}} start_tag = "{{" end_tag = "}}" parameter_tag = "|"

-        descendants_buffer = io.StringIO(descendants_string)

-        for line in descendants_buffer:

-            matches = re.findall(r"(?<={{).*?(?=}})",

-                                 line)  # find all matches for every string between {{ and }} in a non-greedy manner

-            for match in matches:

-                match_split = match.split("|")

-                if (match_split[0] == "l"):

-                    descendant_words.append({"language": match_split[1], "lemma": match_split[2]})

-        return descendant_words

+    wikipage_text_string = get_wikipage_text(title)

+    # ET.dump(root)

+    # print(wikipage_text_string)

+    match = re.search(r"\=+Descendants\=+", wikipage_text_string)

+    descendants_string = wikipage_text_string[match.end():-1]

+    descendant_words = []

+    # {{l|ang|hungor}} start_tag = "{{" end_tag = "}}" parameter_tag = "|"

+    descendants_buffer = io.StringIO(descendants_string)

+    for line in descendants_buffer:

+        matches = re.findall(r"(?<={{).*?(?=}})",

+                             line)  # find all matches for every string between {{ and }} in a non-greedy manner

+        for match in matches:

+            match_split = match.split("|")

+            if (match_split[0] == "l"):

+                descendant_words.append({"language": match_split[1], "lemma": match_split[2]})

+    return descendant_words

 def get_PG_decendants(word):

new file mode 100644

@@ -0,0 +1,27 @@

+import urllib.request

+import urllib.parse

+import xml.etree.ElementTree as ET

+

+def get_wikipage_text(title):

+    request_parameters = {

+            "action": "query",

+            "format": "xml",

+            "export": 1,

+            "exportnowrap": 1,

+            "titles": title,

+            "redirects": 1

+        }

+    request_data = urllib.parse.urlencode(request_parameters)

+    request_data = request_data.encode('utf8')

+    wikipage_request = urllib.request.Request("https://en.wiktionary.org/w/api.php", request_data)

+    print(wikipage_request)

+    with urllib.request.urlopen(wikipage_request) as wikipage_response:

+        # with open("Wiktionary-20170813141826.xml", "r", encoding="utf-8") as wikipage_response:

+        wikipage_string = wikipage_response.read()

+        root = ET.fromstring(wikipage_string)

+        ns = {"mwns": "http://www.mediawiki.org/xml/export-0.10/"}

+        # wikipage_text_string = root.find("./mwns:page/mwns:title", ns).text

+        wikipage_text_string = root.find("./mwns:page/mwns:revision/mwns:text", ns).text

+        # ET.dump(root)

+        # print(wikipage_text_string)

+        return wikipage_text_string

\ No newline at end of file

@@ -74,14 +74,14 @@ def main(args):

             word2 = globalvars["data"]["words"][j]

             if (word1["language"] == word2["language"]): #if languages match

                 wordpair = (word1, word2)

-                compare(wordpair) #compare the pair

+                #compare(wordpair) #compare the pair

     # result = list(map(lambda word: {"language": word["language"], "lemma": myformat(word["lemma"])}, get_PG_decendants("hrītaną")))

     # print(str(result))

-    # ancestor_word = get_ancestor("allègre", "fr", "la")[0]["lemma"]

-    # ancestor_word = ancestor_word.lstrip("*")

-    # print(get_PG_decendants(ancestor_word))

-    print(get_ancestor("allègre", "fr", "la"))

-    print(get_ancestor("allegro", "it", "la"))

+    ancestor_word = get_ancestor("froh", "de", "gem-pro")[0]["lemma"]

+    ancestor_word = ancestor_word.lstrip("*")

+    print(get_PG_decendants(ancestor_word))

+    # print(get_ancestor("allègre", "fr", "la"))

+    # print(get_ancestor("allegro", "it", "la"))

 main(sys.argv[1:])