0.0.2 release!

r4l/bin/cli.py

@@ -1,8 +1,10 @@
 #!/usr/bin/env python3
 # -*- coding: utf-8 -*-
 import argparse
+import sys
+
 from r4l.util.text import TextProcessor
-from r4l.util.reader import Reader
+from r4l.util.reader import Reader, models_dict
 import os
 import time
 import csv
@@ -11,14 +13,22 @@
 os.environ["TOKENIZERS_PARALLELISM"] = "False"
 tag_remover = re.compile('<.*?>')
 
+def str2bool(v):
+    if isinstance(v, bool):
+        return v
+    if v.lower() in ("yes", "true", "t", "y", "1"):
+        return True
+    if v.lower() in ("no", "false", "f", "n", "0"):
+        return False
+    raise argparse.ArgumentTypeError("Boolean value expected.")
 
 def get_ext(filename):
     return filename.split(".")[-1]
 
 
-def get_texts(sesspath, force_english):
+def get_texts(sesspath, lang, force_english):
     wordcount = 0
-    tp = TextProcessor()
+    tp = TextProcessor(sc_langs=lang)
     files = [f for f in os.listdir(sesspath) if get_ext(f) in ['pdf', 'txt', 'muse']]
     texts = [[] for _ in files]
     print(f"> Reading {files}")
@@ -43,8 +53,8 @@ def get_texts(sesspath, force_english):
     return texts, files, wordcount
 
 
-def read_texts(texts, files, outpath):
-    reader = Reader(outpath, lang='en')
+def read_texts(texts, files, outpath, lang):
+    reader = Reader(outpath, lang=lang)
     for text, name in zip(texts, files):
         reader.tts(text, name)
     return
@@ -56,27 +66,42 @@ def main():
                     """In the interests of user-friendliness, this cli will be kept pretty bare-bones"""
                     """
         Basic usage:
-        $ ./r4l/bin/cli.py [--in_path in/] [--out_path out/]
-        will convert (english language) pdfs in the folder "in/" and output mp3s to the folder "out/"
+        $ r4l [--in_path in/] [--out_path out/] [--lang "en"]
+        Converts pdfs, txts, muses in the folder "in/" and output mp3s to the folder "out/" with the primary language set to "en"
+        List languages:
+        $ r4l --list_languages
+        Lists available languages (Warning! Not tested on non-latin scripts!)
             """
     )
-    parser.add_argument("--in_path", type=str, default="in/", help="Path containing pdfs to be converted")
-    parser.add_argument("--out_path", type=str, default="out/", help="Output path")
+    parser.add_argument("--in_path", type=str, default="in/", help="Path containing files to be converted.")
+    parser.add_argument("--out_path", type=str, default="out/", help="Output path.")
+    parser.add_argument("--lang", type=str, default="en", help="Two-letter language code.")
+    parser.add_argument(
+        "--list_langs",
+        type=str2bool,
+        nargs="?",
+        const=True,
+        default=False,
+        help="list available languages.",
+    )
     args = parser.parse_args()
+    if args.list_langs:
+        print(models_dict.keys())
+        sys.exit()
     if not os.path.isdir(args.in_path):
         print("input path must exist and contain files!")
         parser.parse_args(["-h"])
     if not os.path.isdir(args.out_path):
         os.mkdir(args.out_path)
-    run(args.in_path, args.out_path)
+    run(args.in_path, args.out_path, args.lang)
     return
 
 
-def run(in_path, out_path):
+def run(in_path, out_path, lang):
     start_time = time.time()
     force_english: bool = False
-    texts, files, wordcount = get_texts(in_path, force_english)
-    read_texts(texts, files, out_path)
+    texts, files, wordcount = get_texts(in_path, lang, force_english)
+    read_texts(texts, files, out_path, lang)
     time_taken = time.time() - start_time
     with open('time_data.csv', 'a') as f:
         writer = csv.writer(f)
@@ -86,4 +111,4 @@ def run(in_path, out_path):
 
 
 if __name__ == "__main__":
-    run("in/", "out/")
+    run("in/", "out/", "en")

setup.py

@@ -7,7 +7,7 @@
     readme = f.read()
 setup(
     name='reading4listeners',
-    version='0.0.1',
+    version='0.0.2',
     packages=['r4l'],
     url='https://github.com/CypherousSkies/reading-for-listeners',
     license=legal,

time_data.csv

@@ -5,3 +5,4 @@
 544,101.4726173877716
 544,69.36171174049377
 544,95.81861162185669
+544,83.5948269367218