Updated readme, config_loader

Author: Sven Siegmund

README.md

@@ -1,10 +1,60 @@
 # rtfparse
 
-RTF Parser
+RTF Parser. So far it can only de-encapsulate HTML content from an RTF, but it properly parses the RTF structure and allows you to write your own custom RTF renderers. The HTML de-encapsulator provided with `rtfparse` is just one such custom renderer which liberates the HTML content from its RTF encapsulation and saves it in a given html file.
 
-## Call for collaboration
+# Dependencies
 
-This RTF parser needs your collaboration. Refer to the RTF Specification and create new parsable objects.
+See `requirements.txt`.
+
+# Installation
+
+Install rtfparse from your local repository with pip:
+
+    pip install ./rtfparse
+
+Installation creates an executable file `rtfparse` in your python scripts folder which should be in your $PATH. 
+
+# First Run
+
+When you run `rtfparse` for the first time it will start a configuration wizard which will guide you through the process of creating a default configuration file and specifying the location of its folders. (These folders don't mean much yet, they are more or less placeholders for upcoming program features.)
+
+In the configuration wizard you can press `A` for care-free automatic configuration, which would look something like this:
+
+```
+    $ rtfparse
+    Config file missing, creating new default config file
+    
+     ____ ____ __ _ ____ _ ____ _  _ ____ ____ ___ _ ____ __ _
+     |___ [__] | \| |--- | |__, |__| |--< |--|  |  | [__] | \|
+     _  _ _ ___  ____ ____ ___
+     |/\| |  /__ |--| |--< |__>
+    
+    
+    ◊ email_rtf (C:\Users\nagidal\rtfparse\email_rtf) does not exist!
+    
+    (A) Automatically configure this and all remaining rtfparse settings
+    (C) Create this path automatically
+    (M) Manually input correct path to use or to create
+    (Q) Quit and edit `email_rtf` in rtfparse_configuration.ini
+    
+    Created directory C:\Users\nagidal\rtfparse
+    Created directory C:\Users\nagidal\rtfparse\email_rtf
+    Created directory C:\Users\nagidal\rtfparse\html
+```
+
+`rtfparse` also creates the folder `.rtfparse` (beginning with a dot) in your home directory where it saves its default configuration and its log files.
+
+# Usage
+
+Use the `rtfparse` executable from the command line. For example if you want to de-encapsulate the HTML from an RTF file, do it like this:
+
+    rtfparse -f "path/to/rtf_file.rtf" -d "path/to/de_encapsulated.html"
+
+Or you can de-encapsulate the HTML from an MS Outlook message, thanks to [extract_msg](https://github.com/TeamMsgExtractor/msg-extractor) and [compressed_rtf](https://github.com/delimitry/compressed_rtf):
+
+    rtfparse -m "path/to/email.msg" -d "path/to/de_encapsulated.html"
+
+Command reference is in `rtfparse --help`.
 
 # RTF Specification Links
 

requirements.txt

@@ -1,2 +1,3 @@
 argcomplete
 extract-msg
+compressed_rtf

src/rtfparse/config_loader.py

@@ -190,7 +190,7 @@ def wizard(self, error: errors.WrongConfiguration, autoconfig: bool) -> None:
         if "path does not exist" in error.message:
             reason = (f"{error.payload.internal_name} ({error.payload.path}) does not exist!")
             options = OrderedDict((
-                    ("A", "Automatically configure this and all remaining claws settings"),
+                    ("A", f"Automatically configure this and all remaining {utils.program_name} settings"),
                     ("C", "Create this path automatically"),
                     ("M", "Manually input correct path to use or to create"),
                     ("Q", f"Quit and edit `{error.payload.internal_name}` in {self.path_to_config_file.name}"),

src/rtfparse/entry.py

@@ -7,16 +7,19 @@
 import logging.config
 import argparse
 import argcomplete
-import io
 from argcomplete.completers import EnvironCompleter as EC
 from itertools import filterfalse
+import io
+import extract_msg as em
+import compressed_rtf as cr
 # Own modules
 from rtfparse import logging_conf
 from rtfparse import errors
 from rtfparse import utils
 from rtfparse import config_loader
 from rtfparse import version
 from rtfparse.parser import Rtf_Parser
+from rtfparse.renderers import encapsulated_html
 
 
 # Setup logging
@@ -48,17 +51,24 @@ def argument_parser() -> argparse.ArgumentParser:
     parser.add_argument("--autoconfig", action="store_true", help="Configure rtfparse automatically").completer = EC
     parser.add_argument("-f", "--file", action="store", metavar="PATH", type=pathlib.Path, help="path to the rtf file").completer = EC
     parser.add_argument("-m", "--msg", action="store", metavar="PATH", type=pathlib.Path, help="Parse RTF from MS Outlook's .msg file").completer = EC
+    parser.add_argument("-d", "--de-encapsulate-html", action="store", metavar="PATH", type=pathlib.Path, help="De-encapsulate HTML from RTF").completer = EC
     return parser
 
 
+def de_encapsulate(rp: Rtf_Parser, target_file: pathlib.Path) -> None:
+    renderer = encapsulated_html.Encapsulated_HTML()
+    with open(target_file, mode="w", encoding="utf-8") as htmlfile:
+        logger.info(f"Rendering the encapsulated HTML")
+        renderer.render(rp.parsed, htmlfile)
+        logger.info(f"Encapsulated HTML rendered")
+
+
 def run(config: config_loader.Config) -> None:
+    rp = Rtf_Parser()
     if config.cli_args.file and config.cli_args.file.exists():
-        rp = Rtf_Parser()
         with open(config.cli_args.file, mode="rb") as rtf_file:
             rp.parse_file(config, rtf_file)
     elif config.cli_args.msg:
-        import extract_msg as em
-        import compressed_rtf as cr
         msg = em.openMsg(f"{config.cli_args.msg}")
         for attachment in msg.attachments:
             with open(config.html / f"{attachment.longFilename}", mode="wb") as att_file:
@@ -67,14 +77,9 @@ def run(config: config_loader.Config) -> None:
         with open((config.email_rtf / config.cli_args.msg.name).with_suffix(".rtf"), mode="wb") as email_rtf:
             email_rtf.write(decompressed_rtf)
         with io.BytesIO(decompressed_rtf) as rtf_file:
-            rp = Rtf_Parser()
             rp.parse_file(config, rtf_file)
-        from rtfparse.renderers import encapsulated_html
-        renderer = encapsulated_html.Encapsulated_HTML()
-        with open((config.html / config.cli_args.msg.name).with_suffix(".html"), mode="w", encoding="utf-8") as htmlfile:
-            logger.info(f"Rendering the encapsulated HTML")
-            renderer.render(rp.parsed, htmlfile)
-            logger.info(f"Encapsulated HTML rendered")
+    if config.cli_args.de_encapsulate_html:
+        de_encapsulate(rp, config.cli_args.de_encapsulate_html)
 
 
 

src/rtfparse/version.py

@@ -1,4 +1,4 @@
 #!/usr/bin/env python
 
 
-version = "0.6.1"
+version = "0.7.1"