From f20b712d8baec587e9a38b8ba7d5c536e2ba1690 Mon Sep 17 00:00:00 2001
From: Andrew Beveridge <andrew@beveridge.uk>
Date: Sun, 26 Jan 2025 15:08:42 -0500
Subject: [PATCH] Auto-download spacy model

---
 .../correction/phrase_analyzer.py               | 17 +++++++++++++----
 pyproject.toml                                  |  2 +-
 2 files changed, 14 insertions(+), 5 deletions(-)

diff --git a/lyrics_transcriber/correction/phrase_analyzer.py b/lyrics_transcriber/correction/phrase_analyzer.py
index 0741422..b3e1eaa 100644
--- a/lyrics_transcriber/correction/phrase_analyzer.py
+++ b/lyrics_transcriber/correction/phrase_analyzer.py
@@ -21,10 +21,19 @@ def __init__(self, logger: logging.Logger, language_code: str = "en_core_web_sm"
         try:
             self.nlp = spacy.load(language_code)
         except OSError:
-            self.logger.error(f"Failed to load language model: {language_code}")
-            raise OSError(
-                f"Language model '{language_code}' not found. " f"Please install it with: python -m spacy download {language_code}"
-            )
+            self.logger.info(f"Language model {language_code} not found. Attempting to download...")
+            import subprocess
+
+            try:
+                subprocess.check_call(["python", "-m", "spacy", "download", language_code])
+                self.nlp = spacy.load(language_code)
+                self.logger.info(f"Successfully downloaded and loaded {language_code}")
+            except subprocess.CalledProcessError as e:
+                self.logger.error(f"Failed to download language model: {language_code}")
+                raise OSError(
+                    f"Language model '{language_code}' could not be downloaded. "
+                    f"Please install it manually with: python -m spacy download {language_code}"
+                ) from e
 
     def score_phrase(self, words: List[str], context: str) -> PhraseScore:
         """Score a phrase based on grammatical completeness and natural breaks.
diff --git a/pyproject.toml b/pyproject.toml
index d0df6c5..bbd8293 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "lyrics-transcriber"
-version = "0.32.2"
+version = "0.32.3"
 description = "Automatically create synchronised lyrics files in ASS and MidiCo LRC formats with word-level timestamps, using Whisper and lyrics from Genius and Spotify"
 authors = ["Andrew Beveridge <andrew@beveridge.uk>"]
 license = "MIT"