Mini Shell

# Licensed under the Apache License: http://www.apache.org/licenses/LICENSE-2.0
# For details: https://github.com/nedbat/coveragepy/blob/master/NOTICE.txt

"""A simple Python template renderer, for a nano-subset of Django syntax.

For a detailed discussion of this code, see this chapter from 500 Lines:
http://aosabook.org/en/500L/a-template-engine.html

"""

# Coincidentally named the same as http://code.activestate.com/recipes/496702/

from __future__ import annotations

import re

from typing import (
    Any, Callable, Dict, List, NoReturn, Optional, Set, Union, cast,
)


class TempliteSyntaxError(ValueError):
    """Raised when a template has a syntax error."""
    pass


class TempliteValueError(ValueError):
    """Raised when an expression won't evaluate in a template."""
    pass


class CodeBuilder:
    """Build source code conveniently."""

    def __init__(self, indent: int = 0) -> None:
        self.code: List[Union[str, CodeBuilder]] = []
        self.indent_level = indent

    def __str__(self) -> str:
        return "".join(str(c) for c in self.code)

    def add_line(self, line: str) -> None:
        """Add a line of source to the code.

        Indentation and newline will be added for you, don't provide them.

        """
        self.code.extend([" " * self.indent_level, line, "\n"])

    def add_section(self) -> CodeBuilder:
        """Add a section, a sub-CodeBuilder."""
        section = CodeBuilder(self.indent_level)
        self.code.append(section)
        return section

    INDENT_STEP = 4      # PEP8 says so!

    def indent(self) -> None:
        """Increase the current indent for following lines."""
        self.indent_level += self.INDENT_STEP

    def dedent(self) -> None:
        """Decrease the current indent for following lines."""
        self.indent_level -= self.INDENT_STEP

    def get_globals(self) -> Dict[str, Any]:
        """Execute the code, and return a dict of globals it defines."""
        # A check that the caller really finished all the blocks they started.
        assert self.indent_level == 0
        # Get the Python source as a single string.
        python_source = str(self)
        # Execute the source, defining globals, and return them.
        global_namespace: Dict[str, Any] = {}
        exec(python_source, global_namespace)
        return global_namespace


class Templite:
    """A simple template renderer, for a nano-subset of Django syntax.

    Supported constructs are extended variable access::

        {{var.modifier.modifier|filter|filter}}

    loops::

        {% for var in list %}...{% endfor %}

    and ifs::

        {% if var %}...{% endif %}

    Comments are within curly-hash markers::

        {# This will be ignored #}

    Lines between `{% joined %}` and `{% endjoined %}` will have lines stripped
    and joined.  Be careful, this could join words together!

    Any of these constructs can have a hyphen at the end (`-}}`, `-%}`, `-#}`),
    which will collapse the white space following the tag.

    Construct a Templite with the template text, then use `render` against a
    dictionary context to create a finished string::

        templite = Templite('''
            <h1>Hello {{name|upper}}!</h1>
            {% for topic in topics %}
                <p>You are interested in {{topic}}.</p>
            {% endif %}
            ''',
            {"upper": str.upper},
        )
        text = templite.render({
            "name": "Ned",
            "topics": ["Python", "Geometry", "Juggling"],
        })

    """
    def __init__(self, text: str, *contexts: Dict[str, Any]) -> None:
        """Construct a Templite with the given `text`.

        `contexts` are dictionaries of values to use for future renderings.
        These are good for filters and global values.

        """
        self.context = {}
        for context in contexts:
            self.context.update(context)

        self.all_vars: Set[str] = set()
        self.loop_vars: Set[str] = set()

        # We construct a function in source form, then compile it and hold onto
        # it, and execute it to render the template.
        code = CodeBuilder()

        code.add_line("def render_function(context, do_dots):")
        code.indent()
        vars_code = code.add_section()
        code.add_line("result = []")
        code.add_line("append_result = result.append")
        code.add_line("extend_result = result.extend")
        code.add_line("to_str = str")

        buffered: List[str] = []

        def flush_output() -> None:
            """Force `buffered` to the code builder."""
            if len(buffered) == 1:
                code.add_line("append_result(%s)" % buffered[0])
            elif len(buffered) > 1:
                code.add_line("extend_result([%s])" % ", ".join(buffered))
            del buffered[:]

        ops_stack = []

        # Split the text to form a list of tokens.
        tokens = re.split(r"(?s)({{.*?}}|{%.*?%}|{#.*?#})", text)

        squash = in_joined = False

        for token in tokens:
            if token.startswith("{"):
                start, end = 2, -2
                squash = (token[-3] == "-")
                if squash:
                    end = -3

                if token.startswith("{#"):
                    # Comment: ignore it and move on.
                    continue
                elif token.startswith("{{"):
                    # An expression to evaluate.
                    expr = self._expr_code(token[start:end].strip())
                    buffered.append("to_str(%s)" % expr)
                else:
                    # token.startswith("{%")
                    # Action tag: split into words and parse further.
                    flush_output()

                    words = token[start:end].strip().split()
                    if words[0] == "if":
                        # An if statement: evaluate the expression to determine if.
                        if len(words) != 2:
                            self._syntax_error("Don't understand if", token)
                        ops_stack.append("if")
                        code.add_line("if %s:" % self._expr_code(words[1]))
                        code.indent()
                    elif words[0] == "for":
                        # A loop: iterate over expression result.
                        if len(words) != 4 or words[2] != "in":
                            self._syntax_error("Don't understand for", token)
                        ops_stack.append("for")
                        self._variable(words[1], self.loop_vars)
                        code.add_line(
                            "for c_{} in {}:".format(
                                words[1],
                                self._expr_code(words[3])
                            )
                        )
                        code.indent()
                    elif words[0] == "joined":
                        ops_stack.append("joined")
                        in_joined = True
                    elif words[0].startswith("end"):
                        # Endsomething.  Pop the ops stack.
                        if len(words) != 1:
                            self._syntax_error("Don't understand end", token)
                        end_what = words[0][3:]
                        if not ops_stack:
                            self._syntax_error("Too many ends", token)
                        start_what = ops_stack.pop()
                        if start_what != end_what:
                            self._syntax_error("Mismatched end tag", end_what)
                        if end_what == "joined":
                            in_joined = False
                        else:
                            code.dedent()
                    else:
                        self._syntax_error("Don't understand tag", words[0])
            else:
                # Literal content.  If it isn't empty, output it.
                if in_joined:
                    token = re.sub(r"\s*\n\s*", "", token.strip())
                elif squash:
                    token = token.lstrip()
                if token:
                    buffered.append(repr(token))

        if ops_stack:
            self._syntax_error("Unmatched action tag", ops_stack[-1])

        flush_output()

        for var_name in self.all_vars - self.loop_vars:
            vars_code.add_line(f"c_{var_name} = context[{var_name!r}]")

        code.add_line("return ''.join(result)")
        code.dedent()
        self._render_function = cast(
            Callable[
                [Dict[str, Any], Callable[..., Any]],
                str
            ],
            code.get_globals()["render_function"],
        )

    def _expr_code(self, expr: str) -> str:
        """Generate a Python expression for `expr`."""
        if "|" in expr:
            pipes = expr.split("|")
            code = self._expr_code(pipes[0])
            for func in pipes[1:]:
                self._variable(func, self.all_vars)
                code = f"c_{func}({code})"
        elif "." in expr:
            dots = expr.split(".")
            code = self._expr_code(dots[0])
            args = ", ".join(repr(d) for d in dots[1:])
            code = f"do_dots({code}, {args})"
        else:
            self._variable(expr, self.all_vars)
            code = "c_%s" % expr
        return code

    def _syntax_error(self, msg: str, thing: Any) -> NoReturn:
        """Raise a syntax error using `msg`, and showing `thing`."""
        raise TempliteSyntaxError(f"{msg}: {thing!r}")

    def _variable(self, name: str, vars_set: Set[str]) -> None:
        """Track that `name` is used as a variable.

        Adds the name to `vars_set`, a set of variable names.

        Raises an syntax error if `name` is not a valid name.

        """
        if not re.match(r"[_a-zA-Z][_a-zA-Z0-9]*$", name):
            self._syntax_error("Not a valid name", name)
        vars_set.add(name)

    def render(self, context: Optional[Dict[str, Any]] = None) -> str:
        """Render this template by applying it to `context`.

        `context` is a dictionary of values to use in this rendering.

        """
        # Make the complete context we'll use.
        render_context = dict(self.context)
        if context:
            render_context.update(context)
        return self._render_function(render_context, self._do_dots)

    def _do_dots(self, value: Any, *dots: str) -> Any:
        """Evaluate dotted expressions at run-time."""
        for dot in dots:
            try:
                value = getattr(value, dot)
            except AttributeError:
                try:
                    value = value[dot]
                except (TypeError, KeyError) as exc:
                    raise TempliteValueError(
                        f"Couldn't evaluate {value!r}.{dot}"
                    ) from exc
            if callable(value):
                value = value()
        return value