Fix small issues, improve error handling and documentation

httplib/parser.py

@@ -1,4 +1,6 @@
 import logging
+import os
+import pathlib
 import re
 import urllib
 from typing import Dict
@@ -85,6 +87,11 @@ def parse_request_line(line: str):
 
 
 def parse_headers(lines):
+    """
+    Parses the lines from the `lines` iterator as headers.
+    @param lines: iterator to retrieve the lines from.
+    @return: A dictionary with header as key and value as value.
+    """
     headers = []
 
     try:
@@ -127,17 +134,21 @@ def parse_headers(lines):
 def check_next_header(headers, next_header: str, next_value: str):
     if next_header == "content-length":
         if "content-length" in headers:
-            logging.error("Multiple content-length headers specified")
-            raise InvalidResponse()
+            raise InvalidResponse("Multiple content-length headers specified")
         if not next_value.isnumeric() or int(next_value) <= 0:
-            logging.error("Invalid content-length value: %r", next_value)
-            raise InvalidResponse()
+            raise InvalidResponse(f"Invalid content-length value: {next_value}")
 
 
 def parse_uri(uri: str):
+    """
+    Parse the specified URI into the host, port and path.
+    If the URI is invalid, this method will try to create one.
+    @param uri: the URI to be parsed
+    @return: A tuple with the host, port and path
+    """
     parsed = urlsplit(uri)
 
-    # If there is no netloc, the given string is not a valid URI, so split on /
+    # If there is no hostname, the given string is not a valid URI, so split on /
     if parsed.hostname:
         host = parsed.hostname
         path = parsed.path
@@ -180,6 +191,12 @@ def urljoin(base, url):
 
 
 def get_charset(headers: Dict[str, str]):
+    """
+    Returns the charset of the content from the headers if found. Otherwise returns `FORMAT`
+
+    @param headers: the headers to retrieve the charset from
+    @return: A charset
+    """
     if "content-type" in headers:
         content_type = headers["content-type"]
         match = re.search(r"charset\s*=\s*([a-z\-0-9]*)", content_type, re.I)
@@ -187,3 +204,17 @@ def get_charset(headers: Dict[str, str]):
             return match.group(1)
 
     return FORMAT
+
+
+def get_relative_save_path(path: str):
+    """
+    Returns the specified path relative to the working directory.
+
+    @param path: the path to compute
+    @return: the relative path
+    """
+
+    path_obj = pathlib.PurePath(path)
+    root = pathlib.PurePath(os.getcwd())
+    rel = path_obj.relative_to(root)
+    return str(rel)