fast-sentence-segment 1.4.1__py3-none-any.whl → 1.4.3__py3-none-any.whl

fast_sentence_segment/cli.py

@@ -2,9 +2,11 @@
 """CLI for fast-sentence-segment."""
 
 import argparse
+import itertools
 import logging
 import os
 import sys
+import threading
 import time
 
 from fast_sentence_segment import segment_text
@@ -21,6 +23,34 @@ YELLOW = "\033[33m"
 RESET = "\033[0m"
 
 
+class Spinner:
+    """Animated spinner for long-running operations."""
+
+    def __init__(self, message: str):
+        self.message = message
+        self.running = False
+        self.thread = None
+        self.frames = itertools.cycle(["⠋", "⠙", "⠹", "⠸", "⠼", "⠴", "⠦", "⠧", "⠇", "⠏"])
+
+    def _spin(self):
+        while self.running:
+            frame = next(self.frames)
+            print(f"\r  {YELLOW}{frame}{RESET} {self.message}", end="", flush=True)
+            time.sleep(0.08)
+
+    def __enter__(self):
+        self.running = True
+        self.thread = threading.Thread(target=self._spin)
+        self.thread.start()
+        return self
+
+    def __exit__(self, *args):
+        self.running = False
+        if self.thread:
+            self.thread.join()
+        print(f"\r  {' ' * (len(self.message) + 4)}\r", end="", flush=True)
+
+
 def _header(title: str):
     print(f"\n{BOLD}{CYAN}{title}{RESET}")
     print(f"{DIM}{'─' * 40}{RESET}")
@@ -113,35 +143,50 @@ def file_main():
     )
     args = parser.parse_args()
 
+    # Echo command immediately
     _header("segment-file")
+    print(f"  {DIM}Segmenting text file into sentences{RESET}")
+    print()
+
+    # Show configuration
     _param("Input", args.input_file)
     _param("Output", args.output_file)
     _param("Size", _file_size(args.input_file))
-    if args.unwrap:
-        _param("Unwrap", "enabled")
-
-    print(f"\n  {YELLOW}Segmenting...{RESET}", end="", flush=True)
+    _param("Unwrap", "enabled" if args.unwrap else "disabled")
+    _param("Normalize quotes", "disabled" if args.no_normalize_quotes else "enabled")
+    print()
 
+    # Step 1: Read file
+    print(f"  {YELLOW}→{RESET} Reading input file...")
     with open(args.input_file, "r", encoding="utf-8") as f:
         text = f.read()
+    print(f"  {GREEN}✓{RESET} Read {len(text):,} characters")
 
+    # Step 2: Segment text
+    print(f"  {YELLOW}→{RESET} Segmenting text...", end="", flush=True)
     start = time.perf_counter()
     normalize = not args.no_normalize_quotes
     sentences = segment_text(
         text.strip(), flatten=True, unwrap=args.unwrap, normalize=normalize,
     )
     elapsed = time.perf_counter() - start
+    print(f"\r  {GREEN}✓{RESET} Segmented into {len(sentences):,} sentences ({elapsed:.2f}s)")
 
+    # Step 3: Write output
+    total = len(sentences)
     with open(args.output_file, "w", encoding="utf-8") as f:
         if args.unwrap:
             f.write(format_grouped_sentences(sentences) + "\n")
+            print(f"  {GREEN}✓{RESET} Written {total:,} sentences to {args.output_file}")
         else:
-            for sentence in sentences:
+            for i, sentence in enumerate(sentences, 1):
                 f.write(sentence + "\n")
+                if i % 500 == 0 or i == total:
+                    pct = (i / total) * 100
+                    print(f"\r  {YELLOW}→{RESET} Writing... {pct:.0f}% ({i:,}/{total:,})", end="", flush=True)
+            print(f"\r  {GREEN}✓{RESET} Written {total:,} sentences to {args.output_file}       ")
 
-    print(f"\r  {' ' * 20}\r", end="")
-    _done(f"{len(sentences):,} sentences in {elapsed:.2f}s")
-    _done(f"Written to {args.output_file}")
+    print(f"\n  {GREEN}Done!{RESET}")
     print()
 
 

fast_sentence_segment/svc/perform_sentence_segmentation.py

@@ -3,10 +3,46 @@
 """ Sentence Segmentation """
 
 
+import subprocess
+import sys
+
 import spacy
 
 from fast_sentence_segment.core import BaseObject
 
+
+def _load_spacy_model(model_name: str = "en_core_web_sm"):
+    """Load spaCy model, auto-downloading if not found."""
+    # ANSI color codes
+    bold = "\033[1m"
+    cyan = "\033[36m"
+    green = "\033[32m"
+    yellow = "\033[33m"
+    reset = "\033[0m"
+
+    try:
+        return spacy.load(model_name)
+    except OSError:
+        print(f"\n{bold}{cyan}fast-sentence-segment{reset}", file=sys.stderr)
+        print(f"{'─' * 40}", file=sys.stderr)
+        print(
+            f"  {yellow}⚠{reset}  spaCy model '{model_name}' not found.",
+            file=sys.stderr,
+        )
+        print(f"  {yellow}⏳{reset} Downloading model (one-time setup)...", file=sys.stderr)
+        print(file=sys.stderr)
+
+        subprocess.check_call(
+            [sys.executable, "-m", "spacy", "download", model_name],
+        )
+
+        print(file=sys.stderr)
+        print(f"  {green}✓{reset}  Model '{model_name}' installed successfully.", file=sys.stderr)
+        print(f"  {green}✓{reset}  You won't see this message again.", file=sys.stderr)
+        print(file=sys.stderr)
+
+        return spacy.load(model_name)
+
 from fast_sentence_segment.dmo import AbbreviationMerger
 from fast_sentence_segment.dmo import AbbreviationSplitter
 from fast_sentence_segment.dmo import TitleNameMerger
@@ -45,7 +81,7 @@ class PerformSentenceSegmentation(BaseObject):
         """
         BaseObject.__init__(self, __name__)
         if not self.__nlp:
-            self.__nlp = spacy.load("en_core_web_sm")
+            self.__nlp = _load_spacy_model("en_core_web_sm")
 
         self._dehyphenate = Dehyphenator.process
         self._newlines_to_periods = NewlinesToPeriods.process

{fast_sentence_segment-1.4.1.dist-info → fast_sentence_segment-1.4.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: fast-sentence-segment
-Version: 1.4.1
+Version: 1.4.3
 Summary: Fast and Efficient Sentence Segmentation
 Home-page: https://github.com/craigtrim/fast-sentence-segment
 License: MIT
@@ -33,7 +33,7 @@ Description-Content-Type: text/markdown
 
 [![PyPI version](https://img.shields.io/pypi/v/fast-sentence-segment.svg)](https://pypi.org/project/fast-sentence-segment/)
 [![Python versions](https://img.shields.io/pypi/pyversions/fast-sentence-segment.svg)](https://pypi.org/project/fast-sentence-segment/)
-[![CI](https://img.shields.io/github/actions/workflow/status/craigtrim/fast-sentence-segment/ci.yml?branch=master&label=CI)](https://github.com/craigtrim/fast-sentence-segment/actions/workflows/ci.yml)
+[![Tests](https://img.shields.io/badge/tests-664-brightgreen)](https://github.com/craigtrim/fast-sentence-segment/tree/master/tests)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 [![Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json)](https://github.com/astral-sh/ruff)
 [![Downloads](https://static.pepy.tech/badge/fast-sentence-segment)](https://pepy.tech/project/fast-sentence-segment)

{fast_sentence_segment-1.4.1.dist-info → fast_sentence_segment-1.4.3.dist-info}/RECORD

@@ -1,7 +1,7 @@
 fast_sentence_segment/__init__.py,sha256=jeb4yCy89ivyqbo-4ldJLquPAG_XR_33Q7nrDjqPxvE,1465
 fast_sentence_segment/bp/__init__.py,sha256=j2-WfQ9WwVuXeGSjvV6XLVwEdvau8sdAQe4Pa4DrYi8,33
 fast_sentence_segment/bp/segmenter.py,sha256=UW6DguPgA56h-pPYRsfJhjIzBe40j6NdjkwYxamASyA,1928
-fast_sentence_segment/cli.py,sha256=Y89BH-xbJ0vykg301D2543MtGP4kYLnA6i3UQ7Hg5YA,3869
+fast_sentence_segment/cli.py,sha256=vr1Gh-pq4bIPcnhUF6c7ckGdEfoyrI_r0XcrJrIfjEA,5640
 fast_sentence_segment/core/__init__.py,sha256=uoBersYyVStJ5a8zJpQz1GDGaloEdAv2jGHw1292hRM,108
 fast_sentence_segment/core/base_object.py,sha256=AYr7yzusIwawjbKdvcv4yTEnhmx6M583kDZzhzPOmq4,635
 fast_sentence_segment/core/stopwatch.py,sha256=hE6hMz2q6rduaKi58KZmiAL-lRtyh_wWCANhl4KLkRQ,879
@@ -24,9 +24,9 @@ fast_sentence_segment/dmo/title_name_merger.py,sha256=zbG04_VjwM8TtT8LhavvmZqIZL
 fast_sentence_segment/dmo/unwrap_hard_wrapped_text.py,sha256=V1T5RsJBaII_iGJMyWvv6rb2mny8pnVd428oVZL0n5I,2457
 fast_sentence_segment/svc/__init__.py,sha256=9B12mXxBnlalH4OAm1AMLwUMa-RLi2ilv7qhqv26q7g,144
 fast_sentence_segment/svc/perform_paragraph_segmentation.py,sha256=zLKw9rSzb0NNfx4MyEeoGrHwhxTtH5oDrYcAL2LMVHY,1378
-fast_sentence_segment/svc/perform_sentence_segmentation.py,sha256=Qaj7oxVHfUd6pIlwCD1O8P14LaGUdolFGuykmrF6gw8,6276
-fast_sentence_segment-1.4.1.dist-info/LICENSE,sha256=vou5JCLAT5nHcsUv-AkjUYAihYfN9mwPDXxV2DHyHBo,1067
-fast_sentence_segment-1.4.1.dist-info/METADATA,sha256=1movcAzZoI75xuEZwRZD0MauE-yW0vJzpfVQr_PSoW0,7854
-fast_sentence_segment-1.4.1.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-fast_sentence_segment-1.4.1.dist-info/entry_points.txt,sha256=Zc8OwFKj3ofnjy5ZIFqHzDkIEWweV1AP1xap1ZFGD8M,107
-fast_sentence_segment-1.4.1.dist-info/RECORD,,
+fast_sentence_segment/svc/perform_sentence_segmentation.py,sha256=mAJEPWqNQFbnlj7Rb7yiXIRHCAdlgsN0jAbg7e2qpMU,7421
+fast_sentence_segment-1.4.3.dist-info/LICENSE,sha256=vou5JCLAT5nHcsUv-AkjUYAihYfN9mwPDXxV2DHyHBo,1067
+fast_sentence_segment-1.4.3.dist-info/METADATA,sha256=5LGK9z9ip2AtOr2FgaIgkrR2mLvIQaeeuh8gVi3GBaA,7785
+fast_sentence_segment-1.4.3.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+fast_sentence_segment-1.4.3.dist-info/entry_points.txt,sha256=Zc8OwFKj3ofnjy5ZIFqHzDkIEWweV1AP1xap1ZFGD8M,107
+fast_sentence_segment-1.4.3.dist-info/RECORD,,