karaoke-lyrics-processor 0.2.0__py3-none-any.whl → 0.3.1__py3-none-any.whl

karaoke_lyrics_processor/cli.py

@@ -61,7 +61,8 @@ def main():
     processor.process()
     processor.write_to_output_file()
 
-    logger.info(f"Lyrics processing complete, lyrics written to output file: {output_filename}")
+    output_file = processor.output_filename
+    logger.info(f"Lyrics processing complete, lyrics written to output file: {output_file}")
 
 
 if __name__ == "__main__":

karaoke_lyrics_processor/karaoke_lyrics_processor.py

@@ -2,6 +2,10 @@ import re
 import logging
 import pyperclip
 import unicodedata
+import docx2txt
+from striprtf.striprtf import rtf_to_text
+import os
+import codecs
 
 
 class KaraokeLyricsProcessor:
@@ -36,13 +40,56 @@ class KaraokeLyricsProcessor:
         if input_lyrics_text is not None and input_filename is None:
             self.input_lyrics_lines = input_lyrics_text.splitlines()
         elif input_filename is not None and input_lyrics_text is None:
-            self.input_lyrics_lines = self.read_input_lyrics_file()
+            self.input_lyrics_lines = self.read_input_file()
         else:
             raise ValueError("Either input_lyrics or input_filename must be set, but not both.")
 
-    def read_input_lyrics_file(self):
-        with open(self.input_filename, "r") as infile:
-            return infile.readlines()
+    def read_input_file(self):
+        file_extension = os.path.splitext(self.input_filename)[1].lower()
+
+        self.logger.debug(f"Reading input file: {self.input_filename}")
+
+        if file_extension == ".txt":
+            return self.read_txt_file()
+        elif file_extension in [".docx", ".doc"]:
+            return self.read_doc_file()
+        elif file_extension == ".rtf":
+            return self.read_rtf_file()
+        else:
+            raise ValueError(f"Unsupported file format: {file_extension}")
+
+    def read_txt_file(self):
+        with codecs.open(self.input_filename, "r", encoding="utf-8") as infile:
+            content = infile.read()
+        self.logger.debug(f"Raw content read from file: {repr(content)}")
+        lines = content.splitlines()
+        self.logger.debug(f"Number of lines read: {len(lines)}")
+        for i, line in enumerate(lines):
+            self.logger.debug(f"Line {i}: {repr(line)}")
+        return self.clean_text(content).splitlines()
+
+    def read_doc_file(self):
+        text = docx2txt.process(self.input_filename)
+        return self.clean_text(text).splitlines()
+
+    def read_rtf_file(self):
+        with open(self.input_filename, "r", encoding="utf-8") as file:
+            rtf_text = file.read()
+        plain_text = rtf_to_text(rtf_text)
+        return self.clean_text(plain_text).splitlines()
+
+    def clean_text(self, text):
+        self.logger.debug(f"Cleaning text: {repr(text)}")
+        # Remove any non-printable characters except newlines and U+2005 (four-per-em space)
+        cleaned = "".join(char for char in text if char.isprintable() or char in ["\n", "\u2005"])
+        self.logger.debug(f"Text after removing non-printable characters: {repr(cleaned)}")
+        # Replace multiple newlines with a single newline
+        cleaned = re.sub(r"\n{2,}", "\n", cleaned)
+        self.logger.debug(f"Text after replacing multiple newlines: {repr(cleaned)}")
+        # Remove leading/trailing whitespace from each line
+        cleaned = "\n".join(line.strip() for line in cleaned.splitlines())
+        self.logger.debug(f"Final cleaned text: {repr(cleaned)}")
+        return cleaned
 
     def find_best_split_point(self, line):
         """
@@ -82,25 +129,56 @@ class KaraokeLyricsProcessor:
                 self.logger.debug(f"Splitting at middle word index: {mid_word_index}")
                 return split_at_middle
 
-        # If the line is still too long, forcibly split at the maximum length
-        forced_split_point = self.max_line_length
-        if len(line) > forced_split_point:
-            self.logger.debug(f"Line is still too long, forcibly splitting at position {forced_split_point}")
-            return forced_split_point
+        # If the line is still too long, find the last space before max_line_length
+        if len(line) > self.max_line_length:
+            last_space = line.rfind(" ", 0, self.max_line_length)
+            if last_space != -1:
+                self.logger.debug(f"Splitting at last space before max_line_length: {last_space}")
+                return last_space
+            else:
+                # If no space is found, split at max_line_length
+                self.logger.debug(f"No space found, forcibly splitting at max_line_length: {self.max_line_length}")
+                return self.max_line_length
+
+        # If the line is shorter than max_line_length, return its length
+        return len(line)
 
     def replace_non_printable_spaces(self, text):
         """
         Replace non-printable space-like characters, tabs, and other whitespace with regular spaces,
         excluding newline characters.
         """
-        self.logger.debug(f"Replacing non-printable spaces in: {text}")
+        self.logger.debug(f"Replacing non-printable spaces in: {repr(text)}")
+
+        # Log each character and its Unicode code point
+        # for i, char in enumerate(text):
+        #     self.logger.debug(f"Character at position {i}: {repr(char)} (Unicode: U+{ord(char):04X})")
+
         # Define a pattern for space-like characters, including tabs and other whitespace, but excluding newlines
         space_pattern = r"[^\S\n\r]|\u00A0|\u1680|\u2000-\u200A|\u202F|\u205F|\u3000"
+
         # Replace matched characters with a regular space
         cleaned_text = re.sub(space_pattern, " ", text)
+
+        # Log the result of the replacement
+        self.logger.debug(f"Text after replacing non-printable spaces: {repr(cleaned_text)}")
+
         # Remove leading/trailing spaces and collapse multiple spaces into one, preserving newlines
-        cleaned_text = re.sub(r" +", " ", cleaned_text).strip()
-        self.logger.debug(f"Text after replacing non-printable spaces: {cleaned_text}")
+        final_text = re.sub(r" +", " ", cleaned_text).strip()
+
+        # Log the final result
+        self.logger.debug(f"Final text after cleaning: {repr(final_text)}")
+
+        return final_text
+
+    def clean_punctuation_spacing(self, text):
+        """
+        Remove unnecessary spaces before punctuation marks.
+        """
+        self.logger.debug(f"Cleaning punctuation spacing in: {text}")
+        # Remove space before comma, period, exclamation mark, question mark, colon, and semicolon
+        cleaned_text = re.sub(r"\s+([,\.!?:;])", r"\1", text)
+        self.logger.debug(f"Text after cleaning punctuation spacing: {cleaned_text}")
         return cleaned_text
 
     def process_line(self, line):
@@ -110,6 +188,8 @@ class KaraokeLyricsProcessor:
         """
         # Replace non-printable spaces at the beginning
         line = self.replace_non_printable_spaces(line)
+        # Clean up punctuation spacing
+        line = self.clean_punctuation_spacing(line)
 
         processed_lines = []
         iteration_count = 0
@@ -172,8 +252,9 @@ class KaraokeLyricsProcessor:
 
         processed_lyrics_text = "\n".join(lyrics_lines)
 
-        # Final pass to replace any remaining non-printable spaces
+        # Final pass to replace any remaining non-printable spaces and clean punctuation
         processed_lyrics_text = self.replace_non_printable_spaces(processed_lyrics_text)
+        processed_lyrics_text = self.clean_punctuation_spacing(processed_lyrics_text)
 
         self.processed_lyrics_text = processed_lyrics_text
         pyperclip.copy(processed_lyrics_text)
@@ -183,8 +264,11 @@ class KaraokeLyricsProcessor:
         return processed_lyrics_text
 
     def write_to_output_file(self):
+        # Ensure the output filename has a .txt extension
+        base, _ = os.path.splitext(self.output_filename)
+        self.output_filename = f"{base}.txt"
 
-        with open(self.output_filename, "w") as outfile:
+        with open(self.output_filename, "w", encoding="utf-8") as outfile:
             outfile.write(self.processed_lyrics_text)
 
         self.logger.info(f"Processed lyrics written to output file {self.output_filename}")

{karaoke_lyrics_processor-0.2.0.dist-info → karaoke_lyrics_processor-0.3.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: karaoke-lyrics-processor
-Version: 0.2.0
+Version: 0.3.1
 Summary: Process song lyrics to prepare them for karaoke video production, e.g. by splitting long lines
 Home-page: https://github.com/karaokenerds/karaoke-lyrics-processor
 License: MIT
@@ -13,7 +13,10 @@ Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
+Requires-Dist: docx2txt (>=0.8)
 Requires-Dist: pyperclip (>=1.8)
+Requires-Dist: python-docx (>=1)
+Requires-Dist: striprtf (>=0.0.27)
 Project-URL: Documentation, https://github.com/karaokenerds/karaoke-lyrics-processor/blob/main/README.md
 Project-URL: Repository, https://github.com/karaokenerds/karaoke-lyrics-processor
 Description-Content-Type: text/markdown

karaoke_lyrics_processor-0.3.1.dist-info/RECORD

@@ -0,0 +1,8 @@
+karaoke_lyrics_processor/__init__.py,sha256=rLRkJQi61qkRiNXdlTleE3ahJ1oBKcghYVkz64x7IIg,62
+karaoke_lyrics_processor/cli.py,sha256=bdtseRI2jcChb1bMr92pc5mpSWpHXh4TSzA2tknbyjU,2522
+karaoke_lyrics_processor/karaoke_lyrics_processor.py,sha256=qMITsW0SbYCaacvEi9WzuZNeBMJhl2wlMck4WktzTEY,11513
+karaoke_lyrics_processor-0.3.1.dist-info/LICENSE,sha256=BiPihPDxhxIPEx6yAxVfAljD5Bhm_XG2teCbPEj_m0Y,1069
+karaoke_lyrics_processor-0.3.1.dist-info/METADATA,sha256=rCLkfq2I2QkdQlEGI0kiecLb_v5HdcBzuKT0VaNdjJw,4264
+karaoke_lyrics_processor-0.3.1.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
+karaoke_lyrics_processor-0.3.1.dist-info/entry_points.txt,sha256=hjFp6CUxl1p-1WJYfB6TbNcI_DHEnVzX3BXAs4y_0O8,78
+karaoke_lyrics_processor-0.3.1.dist-info/RECORD,,

{karaoke_lyrics_processor-0.2.0.dist-info → karaoke_lyrics_processor-0.3.1.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: poetry-core 1.9.0
+Generator: poetry-core 1.9.1
 Root-Is-Purelib: true
 Tag: py3-none-any

karaoke_lyrics_processor-0.2.0.dist-info/RECORD

@@ -1,8 +0,0 @@
-karaoke_lyrics_processor/__init__.py,sha256=rLRkJQi61qkRiNXdlTleE3ahJ1oBKcghYVkz64x7IIg,62
-karaoke_lyrics_processor/cli.py,sha256=84utSfU-AZZU3okHS8tBFSucJ9-59hXJugfMn48oAKQ,2482
-karaoke_lyrics_processor/karaoke_lyrics_processor.py,sha256=3UOEHFU61aZveDMbPDYcIhAwGc6qKeHRLhwHdY9akLM,7813
-karaoke_lyrics_processor-0.2.0.dist-info/LICENSE,sha256=BiPihPDxhxIPEx6yAxVfAljD5Bhm_XG2teCbPEj_m0Y,1069
-karaoke_lyrics_processor-0.2.0.dist-info/METADATA,sha256=6axf30tfSxbLylh6YF_kfVF2B6CytMoVPKYq2qhB8Tc,4164
-karaoke_lyrics_processor-0.2.0.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-karaoke_lyrics_processor-0.2.0.dist-info/entry_points.txt,sha256=hjFp6CUxl1p-1WJYfB6TbNcI_DHEnVzX3BXAs4y_0O8,78
-karaoke_lyrics_processor-0.2.0.dist-info/RECORD,,