xml functions sorted to appropiate class and fuction. Test cases exte…

…nded
ssciwr · Sep 24, 2024 · e4e3e56 · e4e3e56
1 parent 1731f97
commit e4e3e56
Show file tree

Hide file tree

Showing 4 changed files with 25 additions and 16 deletions.
diff --git a/data/out/dict.out b/data/out/dict.out
@@ -0,0 +1,9 @@
+<?xml version="1.0" encoding="UTF-8" ?><email><content type="str">J&apos;espère que tu vas bien! Je voulais partager avec toi quelques photos de mon dernier voyage!
+[Inline-Bild]
+
+[Inline-Bild]
+
+À bientôt,
+
+Pierre
+</content></email>
diff --git a/mailcom/inout.py b/mailcom/inout.py
@@ -2,6 +2,7 @@
 import os
 import eml_parser
 from bs4 import BeautifulSoup
+from dicttoxml import dicttoxml
 
 class InoutHandler:
     def __init__(self, directory_name: str):
@@ -67,8 +68,10 @@ def get_text(self, file: Path) -> str:
     def validate_data(self):
         pass
 
-    def data_to_xml(self):
-        pass
+    def data_to_xml(self, text):
+        my_item_func = lambda x: 'content'
+        xml = dicttoxml(text, custom_root='email', item_func = my_item_func)  # Different options for review
+        return xml.decode()
 
     def write_file(self, text: str, name: str)-> None:
         """Write the extracted string to a text file.
@@ -78,3 +81,4 @@ def write_file(self, text: str, name: str)-> None:
             name (str): The name of the file to be written."""
         with open("{}.out".format(name), "w") as file:
             file.write(text)
+
diff --git a/mailcom/parse.py b/mailcom/parse.py
@@ -3,8 +3,6 @@
 from transformers import pipeline
 from pathlib import Path
 from mailcom.inout import InoutHandler
-from dicttoxml import dicttoxml
-from xml.dom.minidom import parseString
 
 # please modify this section depending on your setup
 # input language - either "es" or "fr"
@@ -16,6 +14,7 @@
 # path where the output files should be written to
 # this is generated if not present yet
 path_output = Path("../data/out/")
+output_filename = "dict"
 # the ner tool - currently only "transformers"
 tool = "transformers"
 # please do not modify below this section unless you know what you are doing
@@ -126,23 +125,15 @@ def make_dir(path: str):
     for file in io.email_list:
         text = io.get_text(file)
         text = io.get_html_text(text)
+        xml = io.data_to_xml(text)
+        io.write_file(xml, path_output / output_filename)
         # print(text)
         # print(io.email_content["date"])
         # print(io.email_content["attachment"])
         # print(io.email_content["attachement type"])
         # skip this text if email could not be parsed
         if not text:
-            continue
-    xml = dicttoxml(io.email_content["content"])
-    # xml = dicttoxml(io.email_content)  Different options for review
-    xml_decode = xml.decode()
-
-    if check_dir(path_output):
-        xmlfile = open(path_output / "dict.xml", "w")
-        xmlfile.write(xml_decode)
-        xmlfile.close()
-    print(parseString(xml).toprettyxml())
-
+            continue    
         # doc_spacy = nlp_spacy(text)
         # text = get_sentences(doc_spacy)
         # start with first line

diff --git a/mailcom/test/test_inout.py b/mailcom/test/test_inout.py
@@ -9,6 +9,7 @@
 FILE_PATH = Path(pkg / "test" / "data" / "Bonjour Agathe.eml")
 
 TEXT_REF = "J'espère que tu vas bien!"
+XML_REF = "<?xml version=\"1.0\" encoding=\"UTF-8\" ?><email><content type=\"str\">"
 
 @pytest.fixture()
 def get_instant(tmp_path):
@@ -43,9 +44,13 @@ def test_get_text(get_instant):
     assert get_instant.email_content["attachement type"] == ['jpg', 'jpg']
     with pytest.raises(OSError):
         get_instant.get_text(get_instant.directory_name / "nonexisting.eml")
+    return text
 
 def test_get_html_text(get_instant):
     html = """<html><head><title>Test</title></head></html>"""
     assert get_instant.get_html_text(html) == 'Test'
     noHtml = """Test"""
-    assert get_instant.get_html_text(noHtml) == 'Test'
+    assert get_instant.get_html_text(noHtml) == 'Test'
+
+def test_data_to_xml(get_instant):
+    assert get_instant.data_to_xml(test_get_text)[0:66] == XML_REF