Add "access" scope type (cursorless-dev#1519)

- Implements cursorless-dev#707 for Typescript
- Implements cursorless-dev#707 for Python

## Questions

- [ ] Unfortunately, both the queries and tests are almost identically
duplicated between Typescript and Python 😕.
- [ ] I wonder if we should support some kind of templating language, eg
handlebars, along with a meta-updater-style approach where we keep the
generated files in source control as well
- [ ] For the test cases, we could maybe support a list of language ids
in the recorded test yaml 🤷‍♂️
- [ ] Also, should the `.` be considered part of the content range, or
just the removal range?
- [ ] Should a function call on its own be considered `"access"`? eg
`foo()`. What about an identifier on its own, eg `foo`?

## Checklist

- [ ] Make it so eg `bar` or `foo()` on its own is an access? That might
cover a lot of things 🤔. Eg what happens with something in parens? That
could end up as part of access, eg `(a + b).c`
- [ ] What does happen with `(a + b).c`?
- [x] I have added
[tests](https://www.cursorless.org/docs/contributing/test-case-recorder/)
- [x] I have updated the
[docs](https://github.com/cursorless-dev/cursorless/tree/main/docs) and
[cheatsheet](https://github.com/cursorless-dev/cursorless/tree/main/cursorless-talon/src/cheatsheet)
- [x] I have not broken the cheatsheet

Author: pokey

cursorless-talon/src/cheatsheet/get_list.py

@@ -59,8 +59,12 @@ def make_dict_readable(
 
 
 def make_readable(text: str) -> str:
+    text, is_private = (
+        (text[8:], True) if text.startswith("private.") else (text, False)
+    )
     text = text.replace(".", " ")
-    return de_camel(text).lower().capitalize()
+    text = de_camel(text).lower().capitalize()
+    return f"{text} (PRIVATE)" if is_private else text
 
 
 def de_camel(text: str) -> str:

cursorless-talon/src/csv_overrides.py

@@ -35,12 +35,13 @@ def init_csv_and_watch_changes(
     filename: str,
     default_values: dict[str, dict[str, str]],
     extra_ignored_values: Optional[list[str]] = None,
+    extra_allowed_values: Optional[list[str]] = None,
     allow_unknown_values: bool = False,
     default_list_name: Optional[str] = None,
     headers: list[str] = [SPOKEN_FORM_HEADER, CURSORLESS_IDENTIFIER_HEADER],
     ctx: Context = Context(),
     no_update_file: bool = False,
-    pluralize_lists: Optional[list[str]] = [],
+    pluralize_lists: Optional[list[str]] = None,
 ):
     """
     Initialize a cursorless settings csv, creating it if necessary, and watch
@@ -69,8 +70,21 @@ def init_csv_and_watch_changes(
         not update the csv. This is used generally in case there was an issue coming up with the default set of values so we don't want to persist those to disk
         pluralize_lists: Create plural version of given lists
     """
+    # Don't allow both `extra_allowed_values` and `allow_unknown_values`
+    assert not (extra_allowed_values and allow_unknown_values)
+
+    # If `extra_allowed_values` or `allow_unknown_values` is given, we need a
+    # `default_list_name` to put unknown values in
+    assert not (
+        (extra_allowed_values or allow_unknown_values) and not default_list_name
+    )
+
     if extra_ignored_values is None:
         extra_ignored_values = []
+    if extra_allowed_values is None:
+        extra_allowed_values = []
+    if pluralize_lists is None:
+        pluralize_lists = []
 
     file_path = get_full_path(filename)
     super_default_values = get_super_values(default_values)
@@ -83,53 +97,58 @@ def init_csv_and_watch_changes(
     def on_watch(path, flags):
         if file_path.match(path):
             current_values, has_errors = read_file(
-                file_path,
-                headers,
-                super_default_values.values(),
-                extra_ignored_values,
-                allow_unknown_values,
+                path=file_path,
+                headers=headers,
+                default_identifiers=super_default_values.values(),
+                extra_ignored_values=extra_ignored_values,
+                extra_allowed_values=extra_allowed_values,
+                allow_unknown_values=allow_unknown_values,
             )
             update_dicts(
-                default_values,
-                current_values,
-                extra_ignored_values,
-                allow_unknown_values,
-                default_list_name,
-                pluralize_lists,
-                ctx,
+                default_values=default_values,
+                current_values=current_values,
+                extra_ignored_values=extra_ignored_values,
+                extra_allowed_values=extra_allowed_values,
+                allow_unknown_values=allow_unknown_values,
+                default_list_name=default_list_name,
+                pluralize_lists=pluralize_lists,
+                ctx=ctx,
             )
 
     fs.watch(str(file_path.parent), on_watch)
 
     if file_path.is_file():
         current_values = update_file(
-            file_path,
-            headers,
-            super_default_values,
-            extra_ignored_values,
-            allow_unknown_values,
-            no_update_file,
+            path=file_path,
+            headers=headers,
+            default_values=super_default_values,
+            extra_ignored_values=extra_ignored_values,
+            extra_allowed_values=extra_allowed_values,
+            allow_unknown_values=allow_unknown_values,
+            no_update_file=no_update_file,
         )
         update_dicts(
-            default_values,
-            current_values,
-            extra_ignored_values,
-            allow_unknown_values,
-            default_list_name,
-            pluralize_lists,
-            ctx,
+            default_values=default_values,
+            current_values=current_values,
+            extra_ignored_values=extra_ignored_values,
+            extra_allowed_values=extra_allowed_values,
+            allow_unknown_values=allow_unknown_values,
+            default_list_name=default_list_name,
+            pluralize_lists=pluralize_lists,
+            ctx=ctx,
         )
     else:
         if not no_update_file:
             create_file(file_path, headers, super_default_values)
         update_dicts(
-            default_values,
-            super_default_values,
-            extra_ignored_values,
-            allow_unknown_values,
-            default_list_name,
-            pluralize_lists,
-            ctx,
+            default_values=default_values,
+            current_values=super_default_values,
+            extra_ignored_values=extra_ignored_values,
+            extra_allowed_values=extra_allowed_values,
+            allow_unknown_values=allow_unknown_values,
+            default_list_name=default_list_name,
+            pluralize_lists=pluralize_lists,
+            ctx=ctx,
         )
 
     def unsubscribe():
@@ -172,6 +191,7 @@ def update_dicts(
     default_values: dict[str, dict],
     current_values: dict,
     extra_ignored_values: list[str],
+    extra_allowed_values: list[str],
     allow_unknown_values: bool,
     default_list_name: Optional[str],
     pluralize_lists: list[str],
@@ -190,7 +210,7 @@ def update_dicts(
         except KeyError:
             if value in extra_ignored_values:
                 pass
-            elif allow_unknown_values:
+            elif allow_unknown_values or value in extra_allowed_values:
                 results_map[value] = {
                     "key": key,
                     "value": value,
@@ -238,15 +258,17 @@ def update_file(
     headers: list[str],
     default_values: dict[str, str],
     extra_ignored_values: list[str],
+    extra_allowed_values: list[str],
     allow_unknown_values: bool,
     no_update_file: bool,
 ):
     current_values, has_errors = read_file(
-        path,
-        headers,
-        default_values.values(),
-        extra_ignored_values,
-        allow_unknown_values,
+        path=path,
+        headers=headers,
+        default_identifiers=default_values.values(),
+        extra_ignored_values=extra_ignored_values,
+        extra_allowed_values=extra_allowed_values,
+        allow_unknown_values=allow_unknown_values,
     )
     current_identifiers = current_values.values()
 
@@ -311,6 +333,7 @@ def read_file(
     headers: list[str],
     default_identifiers: Container[str],
     extra_ignored_values: list[str],
+    extra_allowed_values: list[str],
     allow_unknown_values: bool,
 ):
     with open(path) as csv_file:
@@ -353,6 +376,7 @@ def read_file(
         if (
             value not in default_identifiers
             and value not in extra_ignored_values
+            and value not in extra_allowed_values
             and not allow_unknown_values
         ):
             has_errors = True

cursorless-talon/src/spoken_forms.py

@@ -72,6 +72,8 @@ def update():
         handle_csv(
             "modifier_scope_types.csv",
             pluralize_lists=["scope_type"],
+            extra_allowed_values=["private.fieldAccess"],
+            default_list_name="scope_type",
         ),
         handle_csv(
             "experimental/wrapper_snippets.csv",

packages/common/src/types/command/PartialTargetDescriptor.types.ts

@@ -105,6 +105,7 @@ export type SimpleScopeTypeType =
   | "collectionItem"
   | "collectionKey"
   | "comment"
+  | "private.fieldAccess"
   | "functionCall"
   | "functionCallee"
   | "functionName"

packages/cursorless-engine/src/generateSpokenForm/defaultSpokenForms/modifiers.ts

@@ -101,6 +101,7 @@ export const scopeSpokenForms = {
   notebookCell: "cell",
 
   switchStatementSubject: null,
+  ["private.fieldAccess"]: null,
 } as const satisfies Record<SimpleScopeTypeType, string | null>;
 
 type ExtendedSurroundingPairName = SurroundingPairName | "whitespace";

packages/cursorless-engine/src/generateSpokenForm/primitiveTargetToSpokenForm.ts

@@ -196,6 +196,7 @@ function scopeTypeToSpokenForm(scopeType: ScopeType): string {
     case "oneOf":
     case "customRegex":
     case "switchStatementSubject":
+    case "private.fieldAccess":
     case "string":
       throw new NoSpokenFormError(`Scope type '${scopeType.type}'`);
     case "surroundingPair": {

packages/cursorless-vscode-e2e/src/suite/fixtures/recorded/languages/python/clearAccessAir.yml

@@ -0,0 +1,29 @@
+languageId: python
+command:
+  version: 5
+  spokenForm: clear access air
+  action: {name: clearAndSetSelection}
+  targets:
+    - type: primitive
+      modifiers:
+        - type: containingScope
+          scopeType: {type: private.fieldAccess}
+      mark: {type: decoratedSymbol, symbolColor: default, character: a}
+  usePrePhraseSnapshot: true
+spokenFormError: Scope type 'private.fieldAccess'
+initialState:
+  documentContents: |
+    aaa().bbb.ccc().ddd
+  selections:
+    - anchor: {line: 1, character: 0}
+      active: {line: 1, character: 0}
+  marks:
+    default.a:
+      start: {line: 0, character: 0}
+      end: {line: 0, character: 3}
+finalState:
+  documentContents: |
+    .bbb.ccc().ddd
+  selections:
+    - anchor: {line: 0, character: 0}
+      active: {line: 0, character: 0}

packages/cursorless-vscode-e2e/src/suite/fixtures/recorded/languages/python/clearAccessBat.yml

@@ -0,0 +1,29 @@
+languageId: python
+command:
+  version: 5
+  spokenForm: clear access bat
+  action: {name: clearAndSetSelection}
+  targets:
+    - type: primitive
+      modifiers:
+        - type: containingScope
+          scopeType: {type: private.fieldAccess}
+      mark: {type: decoratedSymbol, symbolColor: default, character: b}
+  usePrePhraseSnapshot: true
+spokenFormError: Scope type 'private.fieldAccess'
+initialState:
+  documentContents: |
+    aaa().bbb.ccc().ddd
+  selections:
+    - anchor: {line: 1, character: 0}
+      active: {line: 1, character: 0}
+  marks:
+    default.b:
+      start: {line: 0, character: 6}
+      end: {line: 0, character: 9}
+finalState:
+  documentContents: |
+    aaa().ccc().ddd
+  selections:
+    - anchor: {line: 0, character: 5}
+      active: {line: 0, character: 5}

packages/cursorless-vscode-e2e/src/suite/fixtures/recorded/languages/python/clearAccessBat3.yml

@@ -0,0 +1,29 @@
+languageId: python
+command:
+  version: 5
+  spokenForm: clear access bat
+  action: {name: clearAndSetSelection}
+  targets:
+    - type: primitive
+      modifiers:
+        - type: containingScope
+          scopeType: {type: private.fieldAccess}
+      mark: {type: decoratedSymbol, symbolColor: default, character: b}
+  usePrePhraseSnapshot: true
+spokenFormError: Scope type 'private.fieldAccess'
+initialState:
+  documentContents: |
+    a[0].b[c.d]
+  selections:
+    - anchor: {line: 1, character: 0}
+      active: {line: 1, character: 0}
+  marks:
+    default.b:
+      start: {line: 0, character: 5}
+      end: {line: 0, character: 6}
+finalState:
+  documentContents: |
+    a[0]
+  selections:
+    - anchor: {line: 0, character: 4}
+      active: {line: 0, character: 4}

packages/cursorless-vscode-e2e/src/suite/fixtures/recorded/languages/python/clearAccessBat5.yml

@@ -0,0 +1,31 @@
+languageId: python
+command:
+  version: 5
+  spokenForm: clear access bat
+  action: {name: clearAndSetSelection}
+  targets:
+    - type: primitive
+      modifiers:
+        - type: containingScope
+          scopeType: {type: private.fieldAccess}
+      mark: {type: decoratedSymbol, symbolColor: default, character: b}
+  usePrePhraseSnapshot: true
+spokenFormError: Scope type 'private.fieldAccess'
+initialState:
+  documentContents: |
+    aaa.bbb(
+       ccc + 5
+    )
+  selections:
+    - anchor: {line: 3, character: 0}
+      active: {line: 3, character: 0}
+  marks:
+    default.b:
+      start: {line: 0, character: 4}
+      end: {line: 0, character: 7}
+finalState:
+  documentContents: |
+    aaa
+  selections:
+    - anchor: {line: 0, character: 3}
+      active: {line: 0, character: 3}