Release 0.1.1

* Pin RTFDE to lark 1.1.8
* Exclude test modules from being installed as top level module when building the wheel from source.
* Remove unnecessary shebang from non-standalone code
* Updated all licenses to consistently state LGPLv3
* Updated python version to v3.8 and removed use of v3.9 byte-manipulation methods
   - Next major change, when 3.9 is more commonly used, we will push up to 3.9 and revert it forward again.

---------
Co-authored-by: Sandro <shfu29r4bu@liamekaens.com>

CONTRIBUTING.md

@@ -109,14 +109,6 @@ log.setLevel(logging.DEBUG)
 ```
 
 
-
-
-### Grammar Debugging
-
-RTFDE
-
-
-
 ### Lark Debug Logs
 If you want to see underlying Lark language parsing toolkit's logging you can activate its logger like this.
 

RTFDE/__init__.py

@@ -1,12 +1,11 @@
-#!/usr/bin/env python3
 # -*- coding: utf-8 -*-
 # Date Format: YYYY-MM-DD
 #
 # This file is part of RTFDE, a RTF De-Encapsulator.
 # Copyright © 2020 seamus tuohy, <code@seamustuohy.com>
 #
 # This program is free software: you can redistribute it and/or modify it
-# under the terms of the GNU General Public License as published by the Free
+# under the terms of the GNU Lesser General Public License as published by the Free
 # Software Foundation, either version 3 of the License, or (at your option)
 # any later version.
 #
@@ -21,8 +20,8 @@
 """
 
 __author__ = 'seamus tuohy'
-__date__ = '2023-06-18'
-__version__ = '0.1.0'
+__date__ = '2023-12-03'
+__version__ = '0.1.1'
 
 import logging
 from logging import NullHandler

RTFDE/deencapsulate.py

@@ -1,11 +1,10 @@
-#!/usr/bin/env python3
 # -*- coding: utf-8 -*-
 #
 # This file is part of RTFDE, a RTF De-Encapsulator.
 # Copyright © 2020 seamus tuohy, <code@seamustuohy.com>
 #
 # This program is free software: you can redistribute it and/or modify it
-# under the terms of the GNU General Public License as published by the Free
+# under the terms of the GNU Lesser General Public License as published by the Free
 # Software Foundation, either version 3 of the License, or (at your option)
 # any later version.
 #

RTFDE/exceptions.py

@@ -1,11 +1,10 @@
-#!/usr/bin/env python3
 # -*- coding: utf-8 -*-
 #
 # This file is part of RTFDE, a RTF De-Encapsulator.
 # Copyright © 2020 seamus tuohy, <code@seamustuohy.com>
 #
 # This program is free software: you can redistribute it and/or modify it
-# under the terms of the GNU General Public License as published by the Free
+# under the terms of the GNU Lesser General Public License as published by the Free
 # Software Foundation, either version 3 of the License, or (at your option)
 # any later version.
 #

RTFDE/grammar.py

@@ -1,11 +1,10 @@
-#!/usr/bin/env python3
 # -*- coding: utf-8 -*-
 #
 # This file is part of RTFDE, a RTF De-Encapsulator.
 # Copyright © 2020 seamus tuohy, <code@seamustuohy.com>
 #
 # This program is free software: you can redistribute it and/or modify it
-# under the terms of the GNU General Public License as published by the Free
+# under the terms of the GNU Lesser General Public License as published by the Free
 # Software Foundation, either version 3 of the License, or (at your option)
 # any later version.
 #

RTFDE/text_extraction.py

@@ -1,11 +1,10 @@
-#!/usr/bin/env python
 # -*- coding: utf-8 -*-
 #
 # This file is part of RTFDE, a RTF De-Encapsulator.
 # Copyright © 2022 seamus tuohy, <code@seamustuohy.com>
 #
 # This program is free software: you can redistribute it and/or modify it
-# under the terms of the GNU General Public License as published by the Free
+# under the terms of the GNU Lesser General Public License as published by the Free
 # Software Foundation, either version 3 of the License, or (at your option)
 # any later version.
 #
@@ -257,7 +256,12 @@ def unicode_escape_to_chr(item: bytes) -> str:
     ValueError: The escaped unicode character is not valid.
 """
     try:
-        nnnn = int(item.removeprefix(b'\\u')) # raises ValueError if not int.
+        prefix = b'\\u'
+        if item.startswith(prefix):
+            nnnn = item[len(prefix):]
+        else:
+            nnnn = item
+        nnnn = int(nnnn) # raises ValueError if not int.
     except ValueError as _e:
         raise ValueError(f"`{item}` is not a valid escaped unicode character.") from _e
     if nnnn < 0: # § -NNNNN is a negative integer expressed in decimal digits

RTFDE/transformers.py

@@ -1,11 +1,10 @@
-#!/usr/bin/env python3
 # -*- coding: utf-8 -*-
 #
 # This file is part of RTFDE, a RTF De-Encapsulator.
 # Copyright © 2020 seamus tuohy, <code@seamustuohy.com>
 #
 # This program is free software: you can redistribute it and/or modify it
-# under the terms of the GNU General Public License as published by the Free
+# under the terms of the GNU Lesser General Public License as published by the Free
 # Software Foundation, either version 3 of the License, or (at your option)
 # any later version.
 #

RTFDE/utils.py

@@ -1,11 +1,10 @@
-#!/usr/bin/env python
 # -*- coding: utf-8 -*-
 #
 # This file is part of package name, a package description short.
 # Copyright © 2022 seamus tuohy, <code@seamustuohy.com>
 #
 # This program is free software: you can redistribute it and/or modify it
-# under the terms of the GNU General Public License as published by the Free
+# under the terms of the GNU Lesser General Public License as published by the Free
 # Software Foundation, either version 3 of the License, or (at your option)
 # any later version.
 #

docs/RTFDE/deencapsulate.html

@@ -26,14 +26,13 @@ <h1 class="title">Module <code>RTFDE.deencapsulate</code></h1>
 <summary>
 <span>Expand source code</span>
 </summary>
-<pre><code class="python">#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
+<pre><code class="python"># -*- coding: utf-8 -*-
 #
 # This file is part of RTFDE, a RTF De-Encapsulator.
 # Copyright © 2020 seamus tuohy, &lt;code@seamustuohy.com&gt;
 #
 # This program is free software: you can redistribute it and/or modify it
-# under the terms of the GNU General Public License as published by the Free
+# under the terms of the GNU Lesser General Public License as published by the Free
 # Software Foundation, either version 3 of the License, or (at your option)
 # any later version.
 #
@@ -47,12 +46,13 @@ <h1 class="title">Module <code>RTFDE.deencapsulate</code></h1>
 from lark import Lark
 from lark.tree import Tree
 from lark.lexer import Token
+from lark.exceptions import UnexpectedInput
 
 from RTFDE.transformers import RTFCleaner, StripControlWords
 from RTFDE.transformers import StripNonVisibleRTFGroups
 from RTFDE.transformers import StripUnusedSpecialCharacters
 from RTFDE.utils import encode_escaped_control_chars
-from RTFDE.utils import log_validators, log_transformations
+from RTFDE.utils import log_validators, log_transformations, is_logger_on
 from RTFDE.transformers import get_stripped_HTMLRTF_values, DeleteTokensFromTree, strip_binary_objects
 from RTFDE.grammar import make_concise_grammar
 from RTFDE.text_extraction import TextDecoder
@@ -136,8 +136,12 @@ <h1 class="title">Module <code>RTFDE.deencapsulate</code></h1>
             self.found_binary = found_binary
             log.info(&#34;Binary data found and extracted from rtf file.&#34;)
         escaped_rtf = encode_escaped_control_chars(non_binary_rtf)
-        log_transformations(escaped_rtf)
-        self.parse_rtf(escaped_rtf)
+        if is_logger_on(&#34;RTFDE.transform_logger&#34;) is True:
+            log_transformations(escaped_rtf)
+        try:
+            self.parse_rtf(escaped_rtf)
+        except UnexpectedInput as _e:
+            raise MalformedEncapsulatedRtf(f&#34;Malformed encapsulated RTF discovered:&#34;) from _e
         Decoder = TextDecoder()
         Decoder.update_children(self.full_tree)
         self.get_doc_tree()
@@ -260,7 +264,8 @@ <h1 class="title">Module <code>RTFDE.deencapsulate</code></h1>
                            # debug=True,
                            propagate_positions=True)
         self.full_tree = self.parser.parse(rtf)
-        log_transformations(self.full_tree)
+        if is_logger_on(&#34;RTFDE.transform_logger&#34;) is True:
+            log_transformations(self.full_tree)
 
 
     def strip_htmlrtf_tokens(self) -&gt; Tree:
@@ -317,7 +322,8 @@ <h1 class="title">Module <code>RTFDE.deencapsulate</code></h1>
                 operating_tokens.append(token)
             else:
                 operating_tokens += list(token.scan_values(lambda t: t.type == &#39;CONTROLWORD&#39;))
-        log_validators(f&#34;Header tokens being evaluated: {operating_tokens}&#34;)
+        if is_logger_on(&#34;RTFDE.validation_logger&#34;) is True:
+            log_validators(f&#34;Header tokens being evaluated: {operating_tokens}&#34;)
 
         for token in operating_tokens:
             cw_found,found_token = self.check_from_token(token=token, cw_found=cw_found)
@@ -386,7 +392,8 @@ <h1 class="title">Module <code>RTFDE.deencapsulate</code></h1>
         first_token = doc_tree.children[0].value
         if first_token != b&#34;\\rtf1&#34;:
             log.debug(&#34;RTF stream does not contain valid valid RTF document heading. The file must start with \&#34;{\\rtf1\&#34;&#34;)
-            log_validators(f&#34;First child object in document tree is: {first_token!r}&#34;)
+            if is_logger_on(&#34;RTFDE.validation_logger&#34;) is True:
+                log_validators(f&#34;First child object in document tree is: {first_token!r}&#34;)
             raise MalformedRtf(&#34;RTF stream does not start with {\\rtf1&#34;)
 
     @staticmethod
@@ -540,8 +547,12 @@ <h2 id="raises">Raises</h2>
             self.found_binary = found_binary
             log.info(&#34;Binary data found and extracted from rtf file.&#34;)
         escaped_rtf = encode_escaped_control_chars(non_binary_rtf)
-        log_transformations(escaped_rtf)
-        self.parse_rtf(escaped_rtf)
+        if is_logger_on(&#34;RTFDE.transform_logger&#34;) is True:
+            log_transformations(escaped_rtf)
+        try:
+            self.parse_rtf(escaped_rtf)
+        except UnexpectedInput as _e:
+            raise MalformedEncapsulatedRtf(f&#34;Malformed encapsulated RTF discovered:&#34;) from _e
         Decoder = TextDecoder()
         Decoder.update_children(self.full_tree)
         self.get_doc_tree()
@@ -664,7 +675,8 @@ <h2 id="raises">Raises</h2>
                            # debug=True,
                            propagate_positions=True)
         self.full_tree = self.parser.parse(rtf)
-        log_transformations(self.full_tree)
+        if is_logger_on(&#34;RTFDE.transform_logger&#34;) is True:
+            log_transformations(self.full_tree)
 
 
     def strip_htmlrtf_tokens(self) -&gt; Tree:
@@ -721,7 +733,8 @@ <h2 id="raises">Raises</h2>
                 operating_tokens.append(token)
             else:
                 operating_tokens += list(token.scan_values(lambda t: t.type == &#39;CONTROLWORD&#39;))
-        log_validators(f&#34;Header tokens being evaluated: {operating_tokens}&#34;)
+        if is_logger_on(&#34;RTFDE.validation_logger&#34;) is True:
+            log_validators(f&#34;Header tokens being evaluated: {operating_tokens}&#34;)
 
         for token in operating_tokens:
             cw_found,found_token = self.check_from_token(token=token, cw_found=cw_found)
@@ -790,7 +803,8 @@ <h2 id="raises">Raises</h2>
         first_token = doc_tree.children[0].value
         if first_token != b&#34;\\rtf1&#34;:
             log.debug(&#34;RTF stream does not contain valid valid RTF document heading. The file must start with \&#34;{\\rtf1\&#34;&#34;)
-            log_validators(f&#34;First child object in document tree is: {first_token!r}&#34;)
+            if is_logger_on(&#34;RTFDE.validation_logger&#34;) is True:
+                log_validators(f&#34;First child object in document tree is: {first_token!r}&#34;)
             raise MalformedRtf(&#34;RTF stream does not start with {\\rtf1&#34;)
 
     @staticmethod
@@ -952,7 +966,8 @@ <h2 id="raises">Raises</h2>
         first_token = doc_tree.children[0].value
         if first_token != b&#34;\\rtf1&#34;:
             log.debug(&#34;RTF stream does not contain valid valid RTF document heading. The file must start with \&#34;{\\rtf1\&#34;&#34;)
-            log_validators(f&#34;First child object in document tree is: {first_token!r}&#34;)
+            if is_logger_on(&#34;RTFDE.validation_logger&#34;) is True:
+                log_validators(f&#34;First child object in document tree is: {first_token!r}&#34;)
             raise MalformedRtf(&#34;RTF stream does not start with {\\rtf1&#34;)</code></pre>
 </details>
 </dd>
@@ -981,8 +996,12 @@ <h3>Methods</h3>
             self.found_binary = found_binary
             log.info(&#34;Binary data found and extracted from rtf file.&#34;)
         escaped_rtf = encode_escaped_control_chars(non_binary_rtf)
-        log_transformations(escaped_rtf)
-        self.parse_rtf(escaped_rtf)
+        if is_logger_on(&#34;RTFDE.transform_logger&#34;) is True:
+            log_transformations(escaped_rtf)
+        try:
+            self.parse_rtf(escaped_rtf)
+        except UnexpectedInput as _e:
+            raise MalformedEncapsulatedRtf(f&#34;Malformed encapsulated RTF discovered:&#34;) from _e
         Decoder = TextDecoder()
         Decoder.update_children(self.full_tree)
         self.get_doc_tree()
@@ -1148,7 +1167,8 @@ <h2 id="args">Args</h2>
                            # debug=True,
                            propagate_positions=True)
         self.full_tree = self.parser.parse(rtf)
-        log_transformations(self.full_tree)</code></pre>
+        if is_logger_on(&#34;RTFDE.transform_logger&#34;) is True:
+            log_transformations(self.full_tree)</code></pre>
 </details>
 </dd>
 <dt id="RTFDE.deencapsulate.DeEncapsulator.set_content"><code class="name flex">
@@ -1234,7 +1254,8 @@ <h2 id="raises">Raises</h2>
                 operating_tokens.append(token)
             else:
                 operating_tokens += list(token.scan_values(lambda t: t.type == &#39;CONTROLWORD&#39;))
-        log_validators(f&#34;Header tokens being evaluated: {operating_tokens}&#34;)
+        if is_logger_on(&#34;RTFDE.validation_logger&#34;) is True:
+            log_validators(f&#34;Header tokens being evaluated: {operating_tokens}&#34;)
 
         for token in operating_tokens:
             cw_found,found_token = self.check_from_token(token=token, cw_found=cw_found)
@@ -1363,4 +1384,4 @@ <h4><code><a title="RTFDE.deencapsulate.DeEncapsulator" href="#RTFDE.deencapsula
 <p>Generated by <a href="https://pdoc3.github.io/pdoc" title="pdoc: Python API documentation generator"><cite>pdoc</cite> 0.10.0</a>.</p>
 </footer>
 </body>
-</html>
+</html>

docs/RTFDE/exceptions.html

@@ -26,14 +26,13 @@ <h1 class="title">Module <code>RTFDE.exceptions</code></h1>
 <summary>
 <span>Expand source code</span>
 </summary>
-<pre><code class="python">#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
+<pre><code class="python"># -*- coding: utf-8 -*-
 #
 # This file is part of RTFDE, a RTF De-Encapsulator.
 # Copyright © 2020 seamus tuohy, &lt;code@seamustuohy.com&gt;
 #
 # This program is free software: you can redistribute it and/or modify it
-# under the terms of the GNU General Public License as published by the Free
+# under the terms of the GNU Lesser General Public License as published by the Free
 # Software Foundation, either version 3 of the License, or (at your option)
 # any later version.
 #
@@ -200,4 +199,4 @@ <h4><code><a title="RTFDE.exceptions.UnsupportedRTFFormat" href="#RTFDE.exceptio
 <p>Generated by <a href="https://pdoc3.github.io/pdoc" title="pdoc: Python API documentation generator"><cite>pdoc</cite> 0.10.0</a>.</p>
 </footer>
 </body>
-</html>
+</html>

docs/RTFDE/grammar.html

@@ -26,14 +26,13 @@ <h1 class="title">Module <code>RTFDE.grammar</code></h1>
 <summary>
 <span>Expand source code</span>
 </summary>
-<pre><code class="python">#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
+<pre><code class="python"># -*- coding: utf-8 -*-
 #
 # This file is part of RTFDE, a RTF De-Encapsulator.
 # Copyright © 2020 seamus tuohy, &lt;code@seamustuohy.com&gt;
 #
 # This program is free software: you can redistribute it and/or modify it
-# under the terms of the GNU General Public License as published by the Free
+# under the terms of the GNU Lesser General Public License as published by the Free
 # Software Foundation, either version 3 of the License, or (at your option)
 # any later version.
 #
@@ -595,4 +594,4 @@ <h1>Index</h1>
 <p>Generated by <a href="https://pdoc3.github.io/pdoc" title="pdoc: Python API documentation generator"><cite>pdoc</cite> 0.10.0</a>.</p>
 </footer>
 </body>
-</html>
+</html>

docs/RTFDE/index.html

@@ -28,15 +28,14 @@ <h1 class="title">Package <code>RTFDE</code></h1>
 <summary>
 <span>Expand source code</span>
 </summary>
-<pre><code class="python">#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
+<pre><code class="python"># -*- coding: utf-8 -*-
 # Date Format: YYYY-MM-DD
 #
 # This file is part of RTFDE, a RTF De-Encapsulator.
 # Copyright © 2020 seamus tuohy, &lt;code@seamustuohy.com&gt;
 #
 # This program is free software: you can redistribute it and/or modify it
-# under the terms of the GNU General Public License as published by the Free
+# under the terms of the GNU Lesser General Public License as published by the Free
 # Software Foundation, either version 3 of the License, or (at your option)
 # any later version.
 #
@@ -124,4 +123,4 @@ <h1>Index</h1>
 <p>Generated by <a href="https://pdoc3.github.io/pdoc" title="pdoc: Python API documentation generator"><cite>pdoc</cite> 0.10.0</a>.</p>
 </footer>
 </body>
-</html>
+</html>