Migrate language modes to CSV

CHANGELOG.md

@@ -0,0 +1 @@
+August 10 2024: The language modes (that keep track of programming language names, corresponding extensions, and spoken forms) have been migrated to a CSV file. If you have made changes directly to the language_modes.py file to customize that information, you can migrate your changes by letting the new community code run to generate the CSV file and then editing it. Items within the same column can be separated by semicolons if you want to have multiple spoken forms or file extensions associated with the same language.

core/edit_text_file.py

@@ -19,6 +19,7 @@
         "alphabet": "alphabet.csv",
         "directories": "directories.csv",
         "file extensions": "file_extensions.csv",
+        "language modes": "language_modes.csv",
         "search engines": "search_engines.csv",
         "system paths": "system_paths.csv",
         "unix utilities": "unix_utilities.csv",

core/modes/language_modes.py

@@ -1,65 +1,13 @@
-from talon import Context, Module, actions
-
-# Maps language mode names to the extensions that activate them. Only put things
-# here which have a supported language mode; that's why there are so many
-# commented out entries. TODO: make this a csv file?
-language_extensions = {
-    # 'assembly': 'asm s',
-    # 'bash': 'bashbook sh',
-    "batch": "bat",
-    "c": "c h",
-    # 'cmake': 'cmake',
-    # "cplusplus": "cpp hpp",
-    "csharp": "cs",
-    "css": "css",
-    # 'elisp': 'el',
-    # 'elm': 'elm',
-    "gdb": "gdb",
-    "go": "go",
-    "java": "java",
-    "javascript": "js",
-    "javascriptreact": "jsx",
-    # "json": "json",
-    "kotlin": "kt",
-    "lua": "lua",
-    "markdown": "md",
-    # 'perl': 'pl',
-    "php": "php",
-    # 'powershell': 'ps1',
-    "python": "py",
-    "protobuf": "proto",
-    "r": "r",
-    # 'racket': 'rkt',
-    "ruby": "rb",
-    "rust": "rs",
-    "scala": "scala",
-    "scss": "scss",
-    # 'snippets': 'snippets',
-    "sql": "sql",
-    "stata": "do ado",
-    "talon": "talon",
-    "talonlist": "talon-list",
-    "terraform": "tf",
-    "tex": "tex",
-    "typescript": "ts",
-    "typescriptreact": "tsx",
-    # 'vba': 'vba',
-    "vimscript": "vim vimrc",
-    # html doesn't actually have a language mode, but we do have snippets.
-    "html": "html",
-}
-
-# Override speakable forms for language modes. If not present, a language mode's
-# name is used directly.
-language_name_overrides = {
-    "cplusplus": ["see plus plus"],
-    "csharp": ["see sharp"],
-    "css": ["c s s"],
-    "gdb": ["g d b"],
-    "go": ["go", "go lang", "go language"],
-    "r": ["are language"],
-    "tex": ["tech", "lay tech", "latex"],
-}
+from typing import Callable
+
+from talon import Context, Module, actions, resource
+
+from ..user_settings import (
+    compute_csv_path,
+    compute_spoken_form_to_key_dictionary,
+    create_three_columns_csv_from_default_if_nonexistent,
+    get_key_value_pairs_and_spoken_forms_from_three_column_csv,
+)
 
 mod = Module()
 
@@ -74,20 +22,165 @@
 mod.tag("code_language_forced", "This tag is active when a language mode is forced")
 mod.list("language_mode", desc="Name of a programming language mode.")
 
-ctx.lists["self.language_mode"] = {
-    name: language
-    for language in language_extensions
-    for name in language_name_overrides.get(language, [language])
-}
-
 # Maps extension to languages.
-extension_lang_map = {
-    "." + ext: language
-    for language, extensions in language_extensions.items()
-    for ext in extensions.split()
-}
-
-language_ids = set(language_extensions.keys())
+extension_lang_map = None
+
+language_ids = None
+language_extensions = None
+
+SETTINGS_FILENAME = "language_modes.csv"
+settings_filepath = compute_csv_path(SETTINGS_FILENAME)
+
+LANGUAGE_HEADERS = ["language", "extensions", "spoken_forms"]
+
+language_mode_update_callbacks = {}
+
+
+def make_sure_settings_file_exists():
+    # Maps language mode names to the extensions that activate them and language spoken forms. Only put things
+    # here which have a supported language mode or snippets; that's why there are so many
+    # commented out entries.
+    default_csv_contents = [
+        # ['assembly', ('asm', 's'),],
+        # ['bash', ('bashbook', 'sh'),],
+        [
+            "batch",
+            ("bat",),
+        ],
+        [
+            "c",
+            ("c", "h"),
+        ],
+        # ['cmake', ('cmake',),],
+        # ["cplusplus", ("cpp hpp",), ("see plus plus",)],
+        ["csharp", ("cs",), ("see sharp",)],
+        ["css", ("css",), ("c s s",)],
+        # ['elisp', ('el'),],
+        # ['elm', ('elm'),],
+        ["gdb", ("gdb",), ("g d b",)],
+        ["go", ("go",), ("go", "go lang", "go language")],
+        ["java", ("java",)],
+        ["javascript", ("js",)],
+        ["javascriptreact", ("jsx",)],
+        # ["json", ("json",),],
+        [
+            "kotlin",
+            ("kt",),
+        ],
+        [
+            "lua",
+            ("lua",),
+        ],
+        [
+            "markdown",
+            ("md",),
+        ],
+        # ['perl', ('pl',),],
+        [
+            "php",
+            ("php",),
+        ],
+        # ['powershell', ('ps1',),],
+        [
+            "python",
+            ("py",),
+        ],
+        [
+            "protobuf",
+            ("proto",),
+        ],
+        ["r", ("r"), ("are language",)],
+        # ['racket', ('rkt,'),],
+        [
+            "ruby",
+            ("rb",),
+        ],
+        [
+            "rust",
+            ("rs",),
+        ],
+        [
+            "scala",
+            ("scala",),
+        ],
+        [
+            "scss",
+            ("scss",),
+        ],
+        # ['snippets', ('snippets',),],
+        [
+            "sql",
+            ("sql",),
+        ],
+        [
+            "stata",
+            ("do", "ado"),
+        ],
+        [
+            "talon",
+            ("talon",),
+        ],
+        [
+            "talonlist",
+            ("talon-list",),
+        ],
+        [
+            "terraform",
+            ("tf",),
+        ],
+        ["tex", ("tex",), ("tech", "lay tech", "latex")],
+        [
+            "typescript",
+            ("ts",),
+        ],
+        [
+            "typescriptreact",
+            ("tsx",),
+        ],
+        # ['vba', ('vba',),],
+        [
+            "vimscript",
+            ("vim", "vimrc"),
+        ],
+        # html doesn't actually have a language mode, but we do have snippets.
+        [
+            "html",
+            ("html",),
+        ],
+    ]
+    create_three_columns_csv_from_default_if_nonexistent(
+        SETTINGS_FILENAME, LANGUAGE_HEADERS, default_csv_contents
+    )
+
+
+make_sure_settings_file_exists()
+
+
+@resource.watch(settings_filepath)
+def load_language_modes(path: str):
+    global language_extensions, extension_lang_map, language_ids
+    make_sure_settings_file_exists()
+    language_extensions, language_spoken_forms = (
+        get_key_value_pairs_and_spoken_forms_from_three_column_csv(
+            SETTINGS_FILENAME,
+            LANGUAGE_HEADERS,
+        )
+    )
+    ctx.lists["self.language_mode"] = compute_spoken_form_to_key_dictionary(
+        language_extensions, language_spoken_forms
+    )
+    extension_lang_map = {
+        "." + ext: language
+        for language, extensions in language_extensions.items()
+        for ext in extensions
+    }
+    language_ids = set(language_extensions.keys())
+
+    for callback in language_mode_update_callbacks.values():
+        callback()
+
+
+load_language_modes(settings_filepath)
 
 forced_language = ""
 
@@ -122,3 +215,9 @@ def code_clear_language_mode():
         global forced_language
         forced_language = ""
         ctx.tags = []
+
+    def register_language_mode_on_update_callback(
+        name: str, callback: Callable[[], None]
+    ):
+        """Registers a callback to be called when the language mode csv is updated"""
+        language_mode_update_callbacks[name] = callback

core/snippets/snippets.py

@@ -23,17 +23,26 @@
     desc="Directory (relative to Talon user) containing additional snippets",
 )
 
-context_map = {
-    # `_` represents the global context, ie snippets available regardless of language
-    "_": Context(),
-}
-snippets_map = {}
+context_map = None
+
+
+def create_context_map():
+    global context_map
+    context_map = {
+        # `_` represents the global context, ie snippets available regardless of language
+        "_": Context(),
+    }
+
+    # Create a context for each defined language
+    for lang in language_ids:
+        ctx = Context()
+        ctx.matches = f"code.language: {lang}"
+        context_map[lang] = ctx
+
 
-# Create a context for each defined language
-for lang in language_ids:
-    ctx = Context()
-    ctx.matches = f"code.language: {lang}"
-    context_map[lang] = ctx
+create_context_map()
+
+snippets_map = {}
 
 
 def get_setting_dir():
@@ -199,13 +208,21 @@ def create_lists(
     return snippets_map, insertions, insertions_phrase, wrappers
 
 
+def on_language_modes_update():
+    create_context_map()
+    update_snippets()
+
+
 def on_ready():
     fs.watch(str(SNIPPETS_DIR), lambda _1, _2: update_snippets())
 
     if get_setting_dir():
         fs.watch(str(get_setting_dir()), lambda _1, _2: update_snippets())
 
     update_snippets()
+    actions.user.register_language_mode_on_update_callback(
+        "snippets", on_language_modes_update
+    )
 
 
 app.register("ready", on_ready)