Merge branch 'formatter-different-approach' into 'formatter'

Formatter: Try different approach

See merge request gregorni/blueprint-compiler!1

blueprintcompiler/formatter.py

@@ -17,38 +17,68 @@
 #
 # SPDX-License-Identifier: LGPL-3.0-or-later
 
+from enum import Enum
+
 from . import tokenizer
 
-OPENING_TOKENS = ["{"]
+OPENING_TOKENS = ["{", "["]
-CLOSING_TOKENS = ["}"]
+CLOSING_TOKENS = ["}", "]"]
 
-NEWLINE_AFTER = [";", "]", "{", "}"]
+NEWLINE_AFTER = [";"] + OPENING_TOKENS + CLOSING_TOKENS
 
-NO_WHITESPACE_BEFORE = [",", ":", ";", ")"]
+NO_WHITESPACE_BEFORE = [",", ":", ";", ")", "."]
-NO_WHITESPACE_AFTER = ["C_", "_", "(", "["]
+NO_WHITESPACE_AFTER = ["C_", "_", "("]
 
 WHITESPACE_AFTER = [":", ","]
 WHITESPACE_BEFORE = ["{"]
 
 
+class LineType(Enum):
+    STATEMENT = 0
+    BLOCK_OPEN = 1
+    BLOCK_CLOSE = 2
+    CHILD_TYPE = 3
+
+
 class Format:
     def format(data):
         indent_levels = 0
         tokens = tokenizer.tokenize(data)
         tokenized_str = ""
-        last_not_whitespace = None
+        last_not_whitespace = None  # To make line 56 not fail
+        current_line = ""
+        prev_line_type = None
 
         for item in tokens:
             if item.type != tokenizer.TokenType.WHITESPACE:
                 item_as_string = str(item)
 
-                if item_as_string in OPENING_TOKENS:
+                if item_as_string in WHITESPACE_BEFORE:
-                    split_string = tokenized_str.splitlines()
+                    current_line = current_line.strip() + " "
+                elif (
+                    item_as_string in NO_WHITESPACE_BEFORE
+                    or str(last_not_whitespace) in NO_WHITESPACE_AFTER
+                ):
+                    current_line = current_line.strip()
 
-                    split_string.insert(
+                current_line += item_as_string
-                        -2 if split_string[-2].strip().startswith("[") else -1, ""
+
+                if (
+                    item_as_string in NEWLINE_AFTER
+                    or item.type == tokenizer.TokenType.COMMENT
+                ):
+                    if item_as_string in OPENING_TOKENS:
+                        # tokenized_str += (
+                        #     ("\n" * num_newlines) + (indent_levels * "  ") + current_line
+                        # )
+                        # current_line = ""
+                        num_newlines = 1 if prev_line_type == LineType.CHILD_TYPE else 2
+                        prev_line_type = LineType.BLOCK_OPEN
+                        tokenized_str = (
+                            tokenized_str.strip()
+                            + (num_newlines * "\n")
+                            + (indent_levels * "  ")
                         )
-                    tokenized_str = "\n".join(split_string)
 
                         indent_levels += 1
                     elif item_as_string in CLOSING_TOKENS:
@@ -57,28 +87,33 @@ class Format:
                             tokenized_str.strip() + "\n" + (indent_levels * "  ")
                         )
 
-                if item_as_string in WHITESPACE_BEFORE:
+                        # tokenized_str += current_line
-                    tokenized_str = tokenized_str.strip() + " "
+                        # current_line = ""
+
+                        # prev_line_type = (
+                        #     LineType.CHILD_TYPE
+                        #     if current_line.strip().startswith("[")
+                        #     else LineType.BLOCK_CLOSE
+                        # )
+
+                    current_line += "\n" + (indent_levels * "  ")
+                    tokenized_str += current_line
+                    current_line = ""
+
                 elif (
-                    item_as_string in NO_WHITESPACE_BEFORE
+                    item_as_string in WHITESPACE_AFTER
-                    or str(last_not_whitespace) in NO_WHITESPACE_AFTER
+                    or item.type == tokenizer.TokenType.IDENT
                 ):
-                    tokenized_str = tokenized_str.strip()
+                    current_line += " "
-
-                tokenized_str += item_as_string
-
-                if (
-                    item_as_string in NEWLINE_AFTER
-                    or item.type == tokenizer.TokenType.COMMENT
-                ):
-                    tokenized_str += "\n" + (indent_levels * "  ")
-                elif item_as_string in WHITESPACE_AFTER:
-                    tokenized_str += " "
 
                 last_not_whitespace = item
 
-            elif tokenized_str == tokenized_str.strip():
+            # else:
-                tokenized_str += " "
+            #     current_line = current_line.strip() + " "
+
+            tokenized_str = "\n".join(
+                [s.strip() if s.strip() == s else s for s in tokenized_str.splitlines()]
+            )
 
         print(tokenized_str)  # TODO: Remove this when the MR is ready to be merged
 

docs/conf.py

@@ -17,9 +17,9 @@
 
 # -- Project information -----------------------------------------------------
 
-project = 'Blueprint'
+project = "Blueprint"
-copyright = '2021-2023, James Westman'
+copyright = "2021-2023, James Westman"
-author = 'James Westman'
+author = "James Westman"
 
 
 # -- General configuration ---------------------------------------------------
@@ -27,16 +27,15 @@ author = 'James Westman'
 # Add any Sphinx extension module names here, as strings. They can be
 # extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
 # ones.
-extensions = [
+extensions = []
-]
 
 # Add any paths that contain templates here, relative to this directory.
-templates_path = ['_templates']
+templates_path = ["_templates"]
 
 # List of patterns, relative to source directory, that match files and
 # directories to ignore when looking for source files.
 # This pattern also affects html_static_path and html_extra_path.
-exclude_patterns = ['_build', 'Thumbs.db', '.DS_Store']
+exclude_patterns = ["_build", "Thumbs.db", ".DS_Store"]
 
 
 # -- Options for HTML output -------------------------------------------------
@@ -44,11 +43,11 @@ exclude_patterns = ['_build', 'Thumbs.db', '.DS_Store']
 # The theme to use for HTML and HTML Help pages.  See the documentation for
 # a list of builtin themes.
 #
-html_theme = 'furo'
+html_theme = "furo"
 
 # Add any paths that contain custom static files (such as style sheets) here,
 # relative to this directory. They are copied after the builtin static files,
 # so a file named "default.css" will overwrite the builtin "default.css".
-html_static_path = ['_static']
+html_static_path = ["_static"]
 
-html_css_files = ['styles.css']
+html_css_files = ["styles.css"]