eigrel 0.1.0__py3-none-any.whl

eigrel/__init__.py

@@ -0,0 +1,3 @@
+"""Eigrel: a programming language for Data, Machine Learning and AI."""
+
+__version__ = '0.1.0'

eigrel/__main__.py

@@ -0,0 +1,5 @@
+import sys
+
+from eigrel.cli import main
+
+sys.exit(main())

eigrel/cli.py

@@ -0,0 +1,143 @@
+import argparse
+import json
+import sys
+from pathlib import Path
+
+from eigrel import __version__
+from eigrel.compiler import EigrelError, parse, tokenize
+from eigrel.compiler.ast import Program, to_dict
+
+STARTER_PROGRAM = """\
+# A first Eigrel pipeline: load data, pick features, train and evaluate a model.
+
+dataset customers from csv("data/customers.csv")
+
+transform customers {
+    filter age >= 18
+    select age, income, purchases, churned
+}
+
+features customers {
+    age
+    income
+    purchases
+}
+
+model churn = random_forest {
+    trees = 100
+}
+
+train churn {
+    target = churned
+}
+
+evaluate churn {
+    metrics = [accuracy, precision, recall, f1]
+}
+"""
+
+
+def _load(path: str) -> tuple[str, str] | None:
+    try:
+        return Path(path).read_text(encoding='utf-8'), path
+    except OSError as exc:
+        print(f'error: cannot read {path}: {exc.strerror}', file=sys.stderr)
+        return None
+
+
+def _parse_file(path: str) -> Program | None:
+    loaded = _load(path)
+    if loaded is None:
+        return None
+    source, filename = loaded
+    try:
+        return parse(source)
+    except EigrelError as exc:
+        print(exc.render(source, filename), file=sys.stderr)
+        return None
+
+
+def cmd_check(args: argparse.Namespace) -> int:
+    failed = 0
+    for path in args.files:
+        program = _parse_file(path)
+        if program is None:
+            failed += 1
+        else:
+            count = len(program.statements)
+            noun = 'statement' if count == 1 else 'statements'
+            print(f'ok: {path} ({count} {noun})')
+    return 1 if failed else 0
+
+
+def cmd_ast(args: argparse.Namespace) -> int:
+    program = _parse_file(args.file)
+    if program is None:
+        return 1
+    print(json.dumps(to_dict(program), indent=2))
+    return 0
+
+
+def cmd_tokens(args: argparse.Namespace) -> int:
+    loaded = _load(args.file)
+    if loaded is None:
+        return 1
+    source, filename = loaded
+    try:
+        tokens = tokenize(source)
+    except EigrelError as exc:
+        print(exc.render(source, filename), file=sys.stderr)
+        return 1
+    for token in tokens:
+        print(f'{token.loc.line}:{token.loc.column}\t{token.kind.name}\t{token.text}')
+    return 0
+
+
+def cmd_init(args: argparse.Namespace) -> int:
+    root = Path(args.name)
+    if root.exists():
+        print(f'error: {root} already exists', file=sys.stderr)
+        return 1
+    (root / 'data').mkdir(parents=True)
+    (root / 'main.eig').write_text(STARTER_PROGRAM, encoding='utf-8')
+    print(f'created {root}/main.eig')
+    print(f'next: eigrel check {root}/main.eig')
+    return 0
+
+
+def build_parser() -> argparse.ArgumentParser:
+    parser = argparse.ArgumentParser(
+        prog='eigrel',
+        description='Eigrel: a programming language for Data, Machine Learning and AI.',
+    )
+    parser.add_argument('--version', action='version', version=f'eigrel {__version__}')
+    commands = parser.add_subparsers(dest='command', required=True)
+
+    check = commands.add_parser('check', help='parse files and report syntax errors')
+    check.add_argument('files', nargs='+', metavar='FILE')
+    check.set_defaults(handler=cmd_check)
+
+    ast_cmd = commands.add_parser('ast', help='print the syntax tree of a file as JSON')
+    ast_cmd.add_argument('file', metavar='FILE')
+    ast_cmd.set_defaults(handler=cmd_ast)
+
+    tokens = commands.add_parser('tokens', help='print the tokens of a file')
+    tokens.add_argument('file', metavar='FILE')
+    tokens.set_defaults(handler=cmd_tokens)
+
+    init = commands.add_parser('init', help='create a new Eigrel project')
+    init.add_argument('name', metavar='NAME')
+    init.set_defaults(handler=cmd_init)
+
+    return parser
+
+
+def main(argv: list[str] | None = None) -> int:
+    args = build_parser().parse_args(argv)
+    handler = args.handler
+    result: int = handler(args)
+    return result
+
+
+if __name__ == '__main__':
+    sys.exit(main())

eigrel/compiler/__init__.py

@@ -0,0 +1,7 @@
+"""Front end of the Eigrel compiler: lexer, parser and AST."""
+
+from eigrel.compiler.errors import EigrelError, LexError, ParseError
+from eigrel.compiler.lexer import tokenize
+from eigrel.compiler.parser import parse
+
+__all__ = ['EigrelError', 'LexError', 'ParseError', 'parse', 'tokenize']

eigrel/compiler/ast.py

@@ -0,0 +1,158 @@
+from dataclasses import dataclass, field, fields
+from typing import Any
+
+from eigrel.compiler.tokens import Location
+
+
+@dataclass(frozen=True)
+class Node:
+    loc: Location = field(compare=False, kw_only=True)
+
+
+# Expressions
+
+
+@dataclass(frozen=True)
+class Name(Node):
+    value: str
+
+
+@dataclass(frozen=True)
+class IntLiteral(Node):
+    value: int
+
+
+@dataclass(frozen=True)
+class FloatLiteral(Node):
+    value: float
+
+
+@dataclass(frozen=True)
+class StringLiteral(Node):
+    value: str
+
+
+@dataclass(frozen=True)
+class BoolLiteral(Node):
+    value: bool
+
+
+@dataclass(frozen=True)
+class ListExpr(Node):
+    items: tuple['Expr', ...]
+
+
+@dataclass(frozen=True)
+class Call(Node):
+    func: str
+    args: tuple['Expr', ...]
+
+
+@dataclass(frozen=True)
+class Unary(Node):
+    op: str
+    operand: 'Expr'
+
+
+@dataclass(frozen=True)
+class Binary(Node):
+    op: str
+    left: 'Expr'
+    right: 'Expr'
+
+
+Expr = (
+    Name
+    | IntLiteral
+    | FloatLiteral
+    | StringLiteral
+    | BoolLiteral
+    | ListExpr
+    | Call
+    | Unary
+    | Binary
+)
+
+
+# Block contents
+
+
+@dataclass(frozen=True)
+class Param(Node):
+    name: str
+    value: Expr
+
+
+@dataclass(frozen=True)
+class FilterOp(Node):
+    condition: Expr
+
+
+@dataclass(frozen=True)
+class SelectOp(Node):
+    columns: tuple[Name, ...]
+
+
+TransformOp = FilterOp | SelectOp
+
+
+# Statements
+
+
+@dataclass(frozen=True)
+class DatasetDecl(Node):
+    name: str
+    source: Call
+
+
+@dataclass(frozen=True)
+class TransformDecl(Node):
+    dataset: str
+    ops: tuple[TransformOp, ...]
+
+
+@dataclass(frozen=True)
+class FeaturesDecl(Node):
+    dataset: str
+    columns: tuple[Name, ...]
+
+
+@dataclass(frozen=True)
+class ModelDecl(Node):
+    name: str
+    algorithm: str
+    params: tuple[Param, ...]
+
+
+@dataclass(frozen=True)
+class TrainStmt(Node):
+    model: str
+    params: tuple[Param, ...]
+
+
+@dataclass(frozen=True)
+class EvaluateStmt(Node):
+    model: str
+    params: tuple[Param, ...]
+
+
+Statement = DatasetDecl | TransformDecl | FeaturesDecl | ModelDecl | TrainStmt | EvaluateStmt
+
+
+@dataclass(frozen=True)
+class Program(Node):
+    statements: tuple[Statement, ...]
+
+
+def to_dict(value: Any) -> Any:
+    """Convert an AST into plain JSON-serializable data."""
+    if isinstance(value, Node):
+        data: dict[str, Any] = {'node': type(value).__name__}
+        for f in fields(value):
+            if f.name != 'loc':
+                data[f.name] = to_dict(getattr(value, f.name))
+        data['loc'] = {'line': value.loc.line, 'column': value.loc.column}
+        return data
+    if isinstance(value, tuple):
+        return [to_dict(item) for item in value]
+    return value

eigrel/compiler/errors.py

@@ -0,0 +1,33 @@
+from eigrel.compiler.tokens import Location
+
+
+class EigrelError(Exception):
+    """A compile-time error tied to a position in the source file."""
+
+    def __init__(self, message: str, loc: Location) -> None:
+        super().__init__(message)
+        self.message = message
+        self.loc = loc
+
+    def render(self, source: str, filename: str) -> str:
+        """Format the error with the offending line and a caret under the column."""
+        lines = source.splitlines()
+        text = lines[self.loc.line - 1] if 0 < self.loc.line <= len(lines) else ''
+        gutter = ' ' * len(str(self.loc.line))
+        return '\n'.join(
+            [
+                f'error: {self.message}',
+                f'{gutter}--> {filename}:{self.loc.line}:{self.loc.column}',
+                f'{gutter} |',
+                f'{self.loc.line} | {text}',
+                f'{gutter} | {" " * (self.loc.column - 1)}^',
+            ]
+        )
+
+
+class LexError(EigrelError):
+    pass
+
+
+class ParseError(EigrelError):
+    pass

eigrel/compiler/lexer.py

@@ -0,0 +1,126 @@
+from eigrel.compiler.errors import LexError
+from eigrel.compiler.tokens import KEYWORDS, OPERATORS, Location, Token, TokenKind
+
+ESCAPES = {'n': '\n', 't': '\t', '\\': '\\', '"': '"', "'": "'"}
+
+
+class Lexer:
+    def __init__(self, source: str) -> None:
+        self.source = source
+        self.pos = 0
+        self.line = 1
+        self.column = 1
+
+    def tokenize(self) -> list[Token]:
+        tokens: list[Token] = []
+        while True:
+            self._skip_trivia()
+            if self._at_end():
+                tokens.append(Token(TokenKind.EOF, '', self._loc()))
+                return tokens
+            tokens.append(self._next_token())
+
+    def _next_token(self) -> Token:
+        char = self._peek()
+        if char.isalpha() or char == '_':
+            return self._identifier()
+        if char.isdigit():
+            return self._number()
+        if char in ('"', "'"):
+            return self._string()
+        for text, kind in OPERATORS:
+            if self.source.startswith(text, self.pos):
+                loc = self._loc()
+                self._advance(len(text))
+                return Token(kind, text, loc)
+        raise LexError(f'unexpected character {char!r}', self._loc())
+
+    def _identifier(self) -> Token:
+        loc = self._loc()
+        start = self.pos
+        while not self._at_end() and (self._peek().isalnum() or self._peek() == '_'):
+            self._advance()
+        text = self.source[start : self.pos]
+        kind = TokenKind.KEYWORD if text in KEYWORDS else TokenKind.IDENT
+        return Token(kind, text, loc)
+
+    def _number(self) -> Token:
+        loc = self._loc()
+        start = self.pos
+        kind = TokenKind.INT
+        self._digits()
+        if self._peek() == '.' and self._peek(1).isdigit():
+            kind = TokenKind.FLOAT
+            self._advance()
+            self._digits()
+        if self._peek() in ('e', 'E'):
+            offset = 2 if self._peek(1) in ('+', '-') else 1
+            if self._peek(offset).isdigit():
+                kind = TokenKind.FLOAT
+                self._advance(offset)
+                self._digits()
+        if self._peek().isalpha() or self._peek() == '_':
+            raise LexError(f'invalid character {self._peek()!r} in number', self._loc())
+        return Token(kind, self.source[start : self.pos].replace('_', ''), loc)
+
+    def _digits(self) -> None:
+        while self._peek().isdigit() or (self._peek() == '_' and self._peek(1).isdigit()):
+            self._advance()
+
+    def _string(self) -> Token:
+        loc = self._loc()
+        quote = self._peek()
+        self._advance()
+        chars: list[str] = []
+        while True:
+            if self._at_end() or self._peek() == '\n':
+                raise LexError('unterminated string', loc)
+            char = self._peek()
+            if char == quote:
+                self._advance()
+                return Token(TokenKind.STRING, ''.join(chars), loc)
+            if char == '\\':
+                escape_loc = self._loc()
+                self._advance()
+                escaped = self._peek()
+                if escaped not in ESCAPES:
+                    raise LexError(f'unknown escape sequence \\{escaped}', escape_loc)
+                chars.append(ESCAPES[escaped])
+                self._advance()
+                continue
+            chars.append(char)
+            self._advance()
+
+    def _skip_trivia(self) -> None:
+        while not self._at_end():
+            char = self._peek()
+            if char == '#':
+                while not self._at_end() and self._peek() != '\n':
+                    self._advance()
+            elif char.isspace():
+                self._advance()
+            else:
+                return
+
+    def _peek(self, offset: int = 0) -> str:
+        index = self.pos + offset
+        return self.source[index] if index < len(self.source) else ''
+
+    def _advance(self, count: int = 1) -> None:
+        for _ in range(count):
+            if self.source[self.pos] == '\n':
+                self.line += 1
+                self.column = 1
+            else:
+                self.column += 1
+            self.pos += 1
+
+    def _at_end(self) -> bool:
+        return self.pos >= len(self.source)
+
+    def _loc(self) -> Location:
+        return Location(self.line, self.column)
+
+
+def tokenize(source: str) -> list[Token]:
+    return Lexer(source).tokenize()

eigrel/compiler/parser.py

@@ -0,0 +1,261 @@
+from collections.abc import Callable
+
+from eigrel.compiler import ast
+from eigrel.compiler.errors import ParseError
+from eigrel.compiler.lexer import tokenize
+from eigrel.compiler.tokens import Token, TokenKind
+
+COMPARISON_OPS = {
+    TokenKind.EQ,
+    TokenKind.NE,
+    TokenKind.LT,
+    TokenKind.LE,
+    TokenKind.GT,
+    TokenKind.GE,
+}
+ADDITIVE_OPS = {TokenKind.PLUS, TokenKind.MINUS}
+MULTIPLICATIVE_OPS = {TokenKind.STAR, TokenKind.SLASH, TokenKind.PERCENT}
+
+
+class Parser:
+    def __init__(self, tokens: list[Token]) -> None:
+        self.tokens = tokens
+        self.pos = 0
+        self.statement_parsers: dict[str, Callable[[], ast.Statement]] = {
+            'dataset': self._dataset,
+            'transform': self._transform,
+            'features': self._features,
+            'model': self._model,
+            'train': self._train,
+            'evaluate': self._evaluate,
+        }
+
+    def parse_program(self) -> ast.Program:
+        loc = self._peek().loc
+        statements: list[ast.Statement] = []
+        while self._peek().kind is not TokenKind.EOF:
+            statements.append(self._statement())
+        return ast.Program(tuple(statements), loc=loc)
+
+    # Statements
+
+    def _statement(self) -> ast.Statement:
+        token = self._peek()
+        if token.kind is TokenKind.KEYWORD and token.text in self.statement_parsers:
+            return self.statement_parsers[token.text]()
+        expected = ', '.join(f"'{word}'" for word in self.statement_parsers)
+        raise ParseError(f'expected a statement ({expected}), found {token.describe()}', token.loc)
+
+    def _dataset(self) -> ast.DatasetDecl:
+        loc = self._expect_keyword('dataset').loc
+        name = self._expect(TokenKind.IDENT, 'a dataset name').text
+        self._expect_keyword('from')
+        source = self._primary()
+        if not isinstance(source, ast.Call):
+            raise ParseError(
+                'expected a source call after \'from\', like csv("file.csv")', source.loc
+            )
+        return ast.DatasetDecl(name, source, loc=loc)
+
+    def _transform(self) -> ast.TransformDecl:
+        loc = self._expect_keyword('transform').loc
+        dataset = self._expect(TokenKind.IDENT, 'a dataset name').text
+        self._expect(TokenKind.LBRACE, "'{'")
+        ops: list[ast.TransformOp] = []
+        while not self._match(TokenKind.RBRACE):
+            ops.append(self._transform_op())
+        return ast.TransformDecl(dataset, tuple(ops), loc=loc)
+
+    def _transform_op(self) -> ast.TransformOp:
+        token = self._peek()
+        if token.is_keyword('filter'):
+            self._advance()
+            return ast.FilterOp(self._expression(), loc=token.loc)
+        if token.is_keyword('select'):
+            self._advance()
+            columns = [self._column()]
+            while self._match(TokenKind.COMMA):
+                columns.append(self._column())
+            return ast.SelectOp(tuple(columns), loc=token.loc)
+        raise ParseError(
+            f"expected 'filter', 'select' or '}}', found {token.describe()}", token.loc
+        )
+
+    def _features(self) -> ast.FeaturesDecl:
+        loc = self._expect_keyword('features').loc
+        dataset = self._expect(TokenKind.IDENT, 'a dataset name').text
+        self._expect(TokenKind.LBRACE, "'{'")
+        columns: list[ast.Name] = []
+        while not self._match(TokenKind.RBRACE):
+            columns.append(self._column())
+            self._match(TokenKind.COMMA)
+        return ast.FeaturesDecl(dataset, tuple(columns), loc=loc)
+
+    def _model(self) -> ast.ModelDecl:
+        loc = self._expect_keyword('model').loc
+        name = self._expect(TokenKind.IDENT, 'a model name').text
+        self._expect(TokenKind.ASSIGN, "'='")
+        algorithm = self._expect(TokenKind.IDENT, 'an algorithm name').text
+        params = self._param_block() if self._check(TokenKind.LBRACE) else ()
+        return ast.ModelDecl(name, algorithm, params, loc=loc)
+
+    def _train(self) -> ast.TrainStmt:
+        loc = self._expect_keyword('train').loc
+        model = self._expect(TokenKind.IDENT, 'a model name').text
+        return ast.TrainStmt(model, self._param_block(), loc=loc)
+
+    def _evaluate(self) -> ast.EvaluateStmt:
+        loc = self._expect_keyword('evaluate').loc
+        model = self._expect(TokenKind.IDENT, 'a model name').text
+        return ast.EvaluateStmt(model, self._param_block(), loc=loc)
+
+    def _param_block(self) -> tuple[ast.Param, ...]:
+        self._expect(TokenKind.LBRACE, "'{'")
+        params: list[ast.Param] = []
+        seen: set[str] = set()
+        while not self._match(TokenKind.RBRACE):
+            key = self._peek()
+            # Keywords are allowed as keys so blocks can grow (e.g. `model = "llm"`).
+            if key.kind not in (TokenKind.IDENT, TokenKind.KEYWORD):
+                raise ParseError(
+                    f"expected a parameter name or '}}', found {key.describe()}", key.loc
+                )
+            if key.text in seen:
+                raise ParseError(f"duplicate parameter '{key.text}'", key.loc)
+            seen.add(key.text)
+            self._advance()
+            self._expect(TokenKind.ASSIGN, f"'=' after '{key.text}'")
+            params.append(ast.Param(key.text, self._expression(), loc=key.loc))
+            self._match(TokenKind.COMMA)
+        return tuple(params)
+
+    def _column(self) -> ast.Name:
+        token = self._expect(TokenKind.IDENT, 'a column name')
+        return ast.Name(token.text, loc=token.loc)
+
+    # Expressions, lowest precedence first
+
+    def _expression(self) -> ast.Expr:
+        return self._or()
+
+    def _or(self) -> ast.Expr:
+        left = self._and()
+        while self._peek().is_keyword('or'):
+            op = self._advance()
+            left = ast.Binary('or', left, self._and(), loc=op.loc)
+        return left
+
+    def _and(self) -> ast.Expr:
+        left = self._not()
+        while self._peek().is_keyword('and'):
+            op = self._advance()
+            left = ast.Binary('and', left, self._not(), loc=op.loc)
+        return left
+
+    def _not(self) -> ast.Expr:
+        if self._peek().is_keyword('not'):
+            op = self._advance()
+            return ast.Unary('not', self._not(), loc=op.loc)
+        return self._comparison()
+
+    def _comparison(self) -> ast.Expr:
+        left = self._additive()
+        if self._peek().kind in COMPARISON_OPS:
+            op = self._advance()
+            left = ast.Binary(op.text, left, self._additive(), loc=op.loc)
+            if self._peek().kind in COMPARISON_OPS:
+                raise ParseError(
+                    "comparisons cannot be chained; combine them with 'and'",
+                    self._peek().loc,
+                )
+        return left
+
+    def _additive(self) -> ast.Expr:
+        left = self._multiplicative()
+        while self._peek().kind in ADDITIVE_OPS:
+            op = self._advance()
+            left = ast.Binary(op.text, left, self._multiplicative(), loc=op.loc)
+        return left
+
+    def _multiplicative(self) -> ast.Expr:
+        left = self._unary()
+        while self._peek().kind in MULTIPLICATIVE_OPS:
+            op = self._advance()
+            left = ast.Binary(op.text, left, self._unary(), loc=op.loc)
+        return left
+
+    def _unary(self) -> ast.Expr:
+        if self._check(TokenKind.MINUS):
+            op = self._advance()
+            return ast.Unary('-', self._unary(), loc=op.loc)
+        return self._primary()
+
+    def _primary(self) -> ast.Expr:
+        token = self._advance()
+        match token.kind:
+            case TokenKind.INT:
+                return ast.IntLiteral(int(token.text), loc=token.loc)
+            case TokenKind.FLOAT:
+                return ast.FloatLiteral(float(token.text), loc=token.loc)
+            case TokenKind.STRING:
+                return ast.StringLiteral(token.text, loc=token.loc)
+            case TokenKind.KEYWORD if token.text in ('true', 'false'):
+                return ast.BoolLiteral(token.text == 'true', loc=token.loc)
+            case TokenKind.LBRACKET:
+                return ast.ListExpr(self._sequence(TokenKind.RBRACKET, "']'"), loc=token.loc)
+            case TokenKind.LPAREN:
+                inner = self._expression()
+                self._expect(TokenKind.RPAREN, "')'")
+                return inner
+            case TokenKind.IDENT:
+                if self._match(TokenKind.LPAREN):
+                    args = self._sequence(TokenKind.RPAREN, "')'")
+                    return ast.Call(token.text, args, loc=token.loc)
+                return ast.Name(token.text, loc=token.loc)
+        raise ParseError(f'expected an expression, found {token.describe()}', token.loc)
+
+    def _sequence(self, closing: TokenKind, closing_text: str) -> tuple[ast.Expr, ...]:
+        """Comma-separated expressions up to `closing`, allowing a trailing comma."""
+        items: list[ast.Expr] = []
+        while not self._match(closing):
+            items.append(self._expression())
+            if not self._match(TokenKind.COMMA):
+                self._expect(closing, f"',' or {closing_text}")
+                break
+        return tuple(items)
+
+    # Token helpers
+
+    def _peek(self) -> Token:
+        return self.tokens[self.pos]
+
+    def _advance(self) -> Token:
+        token = self.tokens[self.pos]
+        if token.kind is not TokenKind.EOF:
+            self.pos += 1
+        return token
+
+    def _check(self, kind: TokenKind) -> bool:
+        return self._peek().kind is kind
+
+    def _match(self, kind: TokenKind) -> bool:
+        if self._check(kind):
+            self._advance()
+            return True
+        return False
+
+    def _expect(self, kind: TokenKind, what: str) -> Token:
+        token = self._peek()
+        if token.kind is not kind:
+            raise ParseError(f'expected {what}, found {token.describe()}', token.loc)
+        return self._advance()
+
+    def _expect_keyword(self, word: str) -> Token:
+        token = self._peek()
+        if not token.is_keyword(word):
+            raise ParseError(f"expected '{word}', found {token.describe()}", token.loc)
+        return self._advance()
+
+
+def parse(source: str) -> ast.Program:
+    return Parser(tokenize(source)).parse_program()

eigrel/compiler/tokens.py

@@ -0,0 +1,102 @@
+from dataclasses import dataclass
+from enum import Enum
+
+
+class TokenKind(Enum):
+    IDENT = 'identifier'
+    KEYWORD = 'keyword'
+    INT = 'integer'
+    FLOAT = 'float'
+    STRING = 'string'
+
+    LBRACE = '{'
+    RBRACE = '}'
+    LPAREN = '('
+    RPAREN = ')'
+    LBRACKET = '['
+    RBRACKET = ']'
+    COMMA = ','
+    ASSIGN = '='
+
+    EQ = '=='
+    NE = '!='
+    LT = '<'
+    LE = '<='
+    GT = '>'
+    GE = '>='
+
+    PLUS = '+'
+    MINUS = '-'
+    STAR = '*'
+    SLASH = '/'
+    PERCENT = '%'
+
+    EOF = 'end of file'
+
+
+KEYWORDS = frozenset(
+    {
+        'dataset',
+        'from',
+        'transform',
+        'filter',
+        'select',
+        'features',
+        'model',
+        'train',
+        'evaluate',
+        'and',
+        'or',
+        'not',
+        'true',
+        'false',
+    }
+)
+
+# Longest match first, so '<=' wins over '<'.
+OPERATORS: tuple[tuple[str, TokenKind], ...] = (
+    ('==', TokenKind.EQ),
+    ('!=', TokenKind.NE),
+    ('<=', TokenKind.LE),
+    ('>=', TokenKind.GE),
+    ('<', TokenKind.LT),
+    ('>', TokenKind.GT),
+    ('=', TokenKind.ASSIGN),
+    ('{', TokenKind.LBRACE),
+    ('}', TokenKind.RBRACE),
+    ('(', TokenKind.LPAREN),
+    (')', TokenKind.RPAREN),
+    ('[', TokenKind.LBRACKET),
+    (']', TokenKind.RBRACKET),
+    (',', TokenKind.COMMA),
+    ('+', TokenKind.PLUS),
+    ('-', TokenKind.MINUS),
+    ('*', TokenKind.STAR),
+    ('/', TokenKind.SLASH),
+    ('%', TokenKind.PERCENT),
+)
+
+
+@dataclass(frozen=True)
+class Location:
+    line: int
+    column: int
+
+
+@dataclass(frozen=True)
+class Token:
+    kind: TokenKind
+    text: str
+    loc: Location
+
+    def is_keyword(self, word: str) -> bool:
+        return self.kind is TokenKind.KEYWORD and self.text == word
+
+    def describe(self) -> str:
+        if self.kind is TokenKind.EOF:
+            return 'end of file'
+        if self.kind in (TokenKind.IDENT, TokenKind.KEYWORD):
+            return f"{self.kind.value} '{self.text}'"
+        if self.kind in (TokenKind.INT, TokenKind.FLOAT, TokenKind.STRING):
+            return f'{self.kind.value} {self.text}'
+        return f"'{self.text}'"

eigrel-0.1.0.dist-info/METADATA

@@ -0,0 +1,135 @@
+Metadata-Version: 2.4
+Name: eigrel
+Version: 0.1.0
+Summary: A programming language for Data, Machine Learning and AI.
+Author: Nathan Souza
+License-Expression: Apache-2.0
+Requires-Python: >=3.13
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Dynamic: license-file
+
+# Eigrel
+
+**A programming language for Data, Machine Learning and AI.**
+
+> Write what you want. Let the compiler decide how to run it.
+
+🇧🇷 [Leia em português](README.pt-br.md)
+
+Eigrel is a declarative language for data engineering, machine learning and GenAI. You describe
+datasets, transformations, features and models in one language; the compiler decides whether each
+step becomes Python, SQL, Spark or something else.
+
+```eigrel
+dataset customers from csv("data/customers.csv")
+
+transform customers {
+    filter age >= 18
+    select age, income, purchases, churned
+}
+
+features customers {
+    age
+    income
+    purchases
+}
+
+model churn = random_forest {
+    trees = 100
+}
+
+train churn {
+    target = churned
+}
+
+evaluate churn {
+    metrics = [accuracy, precision, recall, f1]
+}
+```
+
+## Status
+
+Eigrel is at **v0.1 — Language**: the lexer, parser and syntax tree are done, and the CLI can
+check files and print their tokens or AST. Nothing executes yet; the compiler, IR and Python backend
+come in v0.2. See the [roadmap](docs/ROADMAP.md).
+
+## Getting started
+
+Install from PyPI (Python 3.13+):
+
+```bash
+pip install eigrel
+eigrel init churn
+eigrel check churn/main.eig
+```
+
+### From source
+
+Requires [uv](https://docs.astral.sh/uv/).
+
+```bash
+make install                     # creates .venv and installs eigrel in editable mode
+.venv/bin/eigrel init churn      # creates churn/main.eig
+.venv/bin/eigrel check churn/main.eig
+```
+
+### CLI
+
+| Command | What it does |
+|---|---|
+| `eigrel check FILE...` | Parses each file and reports syntax errors with line and column |
+| `eigrel ast FILE` | Prints the syntax tree as JSON |
+| `eigrel tokens FILE` | Prints the token stream |
+| `eigrel init NAME` | Creates a project with a starter `main.eig` |
+
+Errors point at the exact spot:
+
+```text
+error: comparisons cannot be chained; combine them with 'and'
+ --> pipeline.eig:4:21
+  |
+4 |     filter age > 18 < 30
+  |                     ^
+```
+
+### Docker
+
+```bash
+make docker-build
+make docker-run      # runs `eigrel check` on examples/ml.eig inside the container
+```
+
+## Language
+
+The full syntax is in [docs/LANGUAGE.md](docs/LANGUAGE.md). Examples live in [`examples/`](examples).
+
+## Project layout
+
+```text
+src/eigrel/
+├── compiler/
+│   ├── tokens.py    token kinds, keywords, source locations
+│   ├── lexer.py     source text → tokens
+│   ├── ast.py       syntax tree nodes and JSON export
+│   ├── parser.py    tokens → syntax tree (recursive descent)
+│   └── errors.py    diagnostics with source excerpts
+└── cli.py           the `eigrel` command
+```
+
+## Development
+
+```bash
+make test            # pytest
+make coverage        # pytest with the 90% coverage gate
+make lint            # ruff check + format check
+make typecheck       # mypy
+make check-examples  # eigrel check examples/*.eig
+```
+
+Commits follow [Conventional Commits](https://www.conventionalcommits.org/); releases and the
+changelog are generated by semantic-release.
+
+## License
+
+Licensed under the [Apache License 2.0](LICENSE).

eigrel-0.1.0.dist-info/RECORD

@@ -0,0 +1,15 @@
+eigrel/__init__.py,sha256=Z2X6JRZVH6UaUQWgMs5g-9t_Lk8HSn1TyJOB-NiL1F4,95
+eigrel/__main__.py,sha256=jysB1t2TW3BREL4czKH_dnI5S4dCTAuddmrm2HxI7_g,58
+eigrel/cli.py,sha256=_WLFsDLKhILty3aR4b9n592ukqqZsdO9oiZ-_Pt4UM0,3891
+eigrel/compiler/__init__.py,sha256=v8mXG5QeO5fyG7_vEew8QvP054dZRcDGYul5zOWQOoc,291
+eigrel/compiler/ast.py,sha256=XdABmJBnYQP6KaniH1ZmwCGAlZr_M7k-g154EVQbNrk,2604
+eigrel/compiler/errors.py,sha256=3c-N7u6OPFRxcSDaoW36CeC8fNMYoPXJ975rQ8rIB2I,1008
+eigrel/compiler/lexer.py,sha256=sjMsRLBbswG27ouHIXmRcR3tZWMlqFF_jY9lGkGDqsA,4345
+eigrel/compiler/parser.py,sha256=d1uQXk8FfHMlEDSId3GRP2QTVIL9a3uT3DbYSMh5i9o,10155
+eigrel/compiler/tokens.py,sha256=2Xv_Jav8_wYDy7hkxjKHVthbdtMmw9TOtuudI8UHQXc,2086
+eigrel-0.1.0.dist-info/licenses/LICENSE,sha256=yVuuHRzgI17MzTVgt3LsHvuX80innw--CmNPDCzO_iw,11358
+eigrel-0.1.0.dist-info/METADATA,sha256=HWsQhk9d5_nZYmdADoKVINKZE5w4HHxh94IStyDmK_o,3344
+eigrel-0.1.0.dist-info/WHEEL,sha256=YVMoNqKzERt-wjUZwJ33xBGAwnFl-4cqbYkTtWa4itE,91
+eigrel-0.1.0.dist-info/entry_points.txt,sha256=RCEqQ52LlxfB1TixjmW2MGD_W5sXdWDDZVJvvXpsc2Y,43
+eigrel-0.1.0.dist-info/top_level.txt,sha256=zObn_6cQzPpZ14h1wjG50zCAct_mxKJ6kEoUzYY4BIc,7
+eigrel-0.1.0.dist-info/RECORD,,

eigrel-0.1.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (84.0.0)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

eigrel-0.1.0.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+eigrel = eigrel.cli:main

eigrel-0.1.0.dist-info/licenses/LICENSE

@@ -0,0 +1,202 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.
+

eigrel-0.1.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+eigrel