Clean code for msigdb.

biothings · Apr 1, 2024 · 31d9e32 · 31d9e32
1 parent 243c800
commit 31d9e32
Show file tree

Hide file tree

Showing 4 changed files with 87 additions and 85 deletions.
diff --git a/src/plugins/msigdb/__init__.py b/src/plugins/msigdb/__init__.py
@@ -1,3 +1,2 @@
 from .dump import msigdbDumper
 from .upload import msigdbUploader
-from .xml_encoder import xmlEncoder
diff --git a/src/plugins/msigdb/dump.py b/src/plugins/msigdb/dump.py
@@ -4,6 +4,8 @@
 import biothings
 import bs4
 import config
+import re
+
 import lxml.etree as ET
 
 biothings.config_for_app(config)
@@ -64,6 +66,47 @@ def create_todump_list(self, force=False):
             # self.to_dump.append({"remote": mouse_url, "local": self.mouse_data_file})
 
 
+    def encode_xml(xml_text: str):
+        # Dictionary for replacements
+        replacements = {
+            '&': '&amp;',
+            '<sup>': '&lt;sup&gt;',
+            '</sup>': '&lt;/sup&gt;',
+            '<sub>': '&lt;sub&gt;',
+            '</sub>': '&lt;/sub&gt;',
+            '<i>': '&lt;i&gt;',
+            '</i>': '&lt;/i&gt;',
+            '<b>': '&lt;b&gt;',
+            '</b>': '&lt;/b&gt;',
+            '<BR/>': '&lt;BR/&gt;',
+            '<br/>': '&lt;br/&gt;',
+            ' "TRP-EGL" ': ' &quot;TRP-EGL&quot; ',
+            ' "Treg" ': ' &quot;Treg&quot; ',
+            '</=': '&lt;/=',
+            '>/=': '&gt;/=',
+            '< ': '&lt; ',
+            '> ': '&gt; ',
+            '<or': '&lt;or',
+            '>or': '&gt;or',
+            ' > ': ' &gt; ',
+            ' < ': ' &lt; ',
+            ' =< ': ' =&lt; ',
+            ' => ': ' =&gt; ',
+            '(': '&#40;',
+            ')': '&#41;'
+        }
+
+        # Apply replacements
+        for pattern, replacement in replacements.items():
+            xml_text = re.sub(re.escape(pattern), replacement, xml_text)
+
+        # Handle remaining cases
+        xml_text = re.sub(r'<([\d_.=-])', r'&lt;\1', xml_text)
+        xml_text = re.sub(r'>([\d_.=-])', r'&gt;\1', xml_text)
+
+        return xml_text
+
+
     def sort_xml(self, file, output_file):
         """Sort XML file by organism
         Args:
@@ -77,8 +120,7 @@ def sort_xml(self, file, output_file):
             xml_text = f.read()
 
         # Encode special characters
-        encoder = xmlEncoder()
-        encoded_xml_string = encoder.encode_xml(xml_text=xml_text)
+        encoded_xml_string = self.encode_xml(xml_text=xml_text)
 
         # For reference, create a file with encoded string
         with open(file + ".encoded", "w", encoding="utf-8") as f:

diff --git a/src/plugins/msigdb/parser.py b/src/plugins/msigdb/parser.py
@@ -1,5 +1,6 @@
 import logging
 import os
+import re
 
 import lxml.etree as ET
 
@@ -18,6 +19,47 @@
 from utils.mygene_lookup import MyGeneLookup
 
 
+def decode_xml(xml_text: str):
+    # Dictionary for replacements
+    replacements = {
+        '&amp;': '&',
+        '&lt;sup&gt;': '<sup>',
+        '&lt;/sup&gt;': '</sup>',
+        '&lt;sub&gt;': '<sub>',
+        '&lt;/sub&gt;': '</sub>',
+        '&lt;i&gt;': '<i>',
+        '&lt;/i&gt;': '</i>',
+        '&lt;b&gt;': '<b>',
+        '&lt;/b&gt;': '</b>',
+        '&lt;BR/&gt;': '<BR/>',
+        '&lt;br/&gt;': '<br/>',
+        '&quot;TRP-EGL&quot;': ' "TRP-EGL" ',
+        '&quot;Treg&quot;': ' "Treg" ',
+        '&lt;=': '</=',
+        '&gt;=': '>/=',
+        '&lt; ': '< ',
+        '&gt; ': '> ',
+        '&lt;or': '<or',
+        '&gt;or': '>or',
+        ' &gt; ': ' > ',
+        ' &lt; ': ' < ',
+        ' =&lt; ': ' =< ',
+        ' =&gt; ': ' => ',
+        '&#40;': '(',
+        '&#41;': ')'
+    }
+
+    # Apply replacements
+    for pattern, replacement in replacements.items():
+        xml_text = xml_text.replace(pattern, replacement)
+
+    # Handle remaining cases
+    xml_text = re.sub(r'&lt;([\d_.=-])', r'<\1', xml_text)
+    xml_text = re.sub(r'&gt;([\d_.=-])', r'>\1', xml_text)
+
+    return xml_text
+
+
 def parse_msigdb(data_folder):
     """
     The XML data provides original gene ids, as well as orthology-converted ones.
@@ -51,9 +93,6 @@ def parse_msigdb(data_folder):
         "8": "cell type signature genesets",
     }
 
-    # Decode special characters
-    encoder = xmlEncoder()
-
     for f in ["human_genesets.xml"]:
         data_file = os.path.join(data_folder, f)
         # File contains newline-delimited XML documents. Each document is a single geneset.
@@ -188,7 +227,7 @@ def parse_msigdb(data_folder):
                     # Replace &amp; by space in all fields of msigdb
                     for key, value in msigdb.items():
                         if isinstance(value, str):
-                            msigdb[key] = encoder.decode_xml(value)
+                            msigdb[key] = decode_xml(value)
 
                     doc["msigdb"] = msigdb
                     # Remove lists with only one item

diff --git a/src/plugins/msigdb/xml_encoder.py b/src/plugins/msigdb/xml_encoder.py
@@ -2,83 +2,5 @@
 
 class xmlEncoder():
 
-    def encode_xml(xml_text: str):
-        # Dictionary for replacements
-        replacements = {
-            '&': '&amp;',
-            '<sup>': '&lt;sup&gt;',
-            '</sup>': '&lt;/sup&gt;',
-            '<sub>': '&lt;sub&gt;',
-            '</sub>': '&lt;/sub&gt;',
-            '<i>': '&lt;i&gt;',
-            '</i>': '&lt;/i&gt;',
-            '<b>': '&lt;b&gt;',
-            '</b>': '&lt;/b&gt;',
-            '<BR/>': '&lt;BR/&gt;',
-            '<br/>': '&lt;br/&gt;',
-            ' "TRP-EGL" ': ' &quot;TRP-EGL&quot; ',
-            ' "Treg" ': ' &quot;Treg&quot; ',
-            '</=': '&lt;/=',
-            '>/=': '&gt;/=',
-            '< ': '&lt; ',
-            '> ': '&gt; ',
-            '<or': '&lt;or',
-            '>or': '&gt;or',
-            ' > ': ' &gt; ',
-            ' < ': ' &lt; ',
-            ' =< ': ' =&lt; ',
-            ' => ': ' =&gt; ',
-            '(': '&#40;',
-            ')': '&#41;'
-        }
 
-        # Apply replacements
-        for pattern, replacement in replacements.items():
-            xml_text = re.sub(re.escape(pattern), replacement, xml_text)
 
-        # Handle remaining cases
-        xml_text = re.sub(r'<([\d_.=-])', r'&lt;\1', xml_text)
-        xml_text = re.sub(r'>([\d_.=-])', r'&gt;\1', xml_text)
-
-        return xml_text
-
-
-    def decode_xml(xml_text: str):
-        # Dictionary for replacements
-        replacements = {
-            '&amp;': '&',
-            '&lt;sup&gt;': '<sup>',
-            '&lt;/sup&gt;': '</sup>',
-            '&lt;sub&gt;': '<sub>',
-            '&lt;/sub&gt;': '</sub>',
-            '&lt;i&gt;': '<i>',
-            '&lt;/i&gt;': '</i>',
-            '&lt;b&gt;': '<b>',
-            '&lt;/b&gt;': '</b>',
-            '&lt;BR/&gt;': '<BR/>',
-            '&lt;br/&gt;': '<br/>',
-            '&quot;TRP-EGL&quot;': ' "TRP-EGL" ',
-            '&quot;Treg&quot;': ' "Treg" ',
-            '&lt;=': '</=',
-            '&gt;=': '>/=',
-            '&lt; ': '< ',
-            '&gt; ': '> ',
-            '&lt;or': '<or',
-            '&gt;or': '>or',
-            ' &gt; ': ' > ',
-            ' &lt; ': ' < ',
-            ' =&lt; ': ' =< ',
-            ' =&gt; ': ' => ',
-            '&#40;': '(',
-            '&#41;': ')'
-        }
-
-        # Apply replacements
-        for pattern, replacement in replacements.items():
-            xml_text = xml_text.replace(pattern, replacement)
-
-        # Handle remaining cases
-        xml_text = re.sub(r'&lt;([\d_.=-])', r'<\1', xml_text)
-        xml_text = re.sub(r'&gt;([\d_.=-])', r'>\1', xml_text)
-
-        return xml_text