diff --git a/.gitmodules b/.gitmodules index 611d4fc..59ee1f9 100644 --- a/.gitmodules +++ b/.gitmodules @@ -1,3 +1,6 @@ [submodule "ucwmac"] path = ucwmac url = git://git.ucw.cz/ucwmac.git +[submodule "src/formatitko/katex-server"] + path = src/formatitko/katex-server + url = https://gitea.ks.matfyz.cz:/KSP/formatitko-katex-server diff --git a/src/formatitko/command.py b/src/formatitko/command.py index 943c304..88686a0 100644 --- a/src/formatitko/command.py +++ b/src/formatitko/command.py @@ -16,7 +16,7 @@ class InlineCommand(Span, Command): if len(content) == 1 and (isinstance(content[0], Para) or isinstance(content[0], Plain)): return Span(*content[0].content) else: - raise InlineError(f"The command {self.attributes['c']} returned multiple Paragraphs and must be executed using `::: {{c={self.attributes['c']}}}\\n:::`.\n\n{content}") + return Div(*content) pass class BlockCommand(Div, Command): diff --git a/src/formatitko/command_env.py b/src/formatitko/command_env.py index 4775db4..a943d6f 100644 --- a/src/formatitko/command_env.py +++ b/src/formatitko/command_env.py @@ -5,4 +5,5 @@ from formatitko.util import parse_string from formatitko.context import Context from formatitko.command import Command +from .nop_processor import NOPProcessor from panflute import Element diff --git a/src/formatitko/command_util.py b/src/formatitko/command_util.py index f11a154..e4af09a 100644 --- a/src/formatitko/command_util.py +++ b/src/formatitko/command_util.py @@ -15,7 +15,7 @@ def parse_command(code: str) -> CommandCallable: indented_code_lines = [] for line in code_lines: indented_code_lines.append(("\t" if tabs else " ")+line) - code = "def command(element: Command, context: Context) -> list[Element]:\n"+"\n".join(indented_code_lines) + code = "def command(element: Command, context: Context, processor: NOPProcessor) -> list[Element]:\n"+"\n".join(indented_code_lines) env = {**command_env.__dict__} exec(code, env) return env["command"] diff --git a/src/formatitko/context.py b/src/formatitko/context.py index e24e3ac..167135c 100644 --- a/src/formatitko/context.py +++ b/src/formatitko/context.py @@ -3,11 +3,10 @@ from panflute import Doc, Element, Div, Span, Header from typing import Union, Callable from types import ModuleType import os -import warnings from .command import Command -CommandCallable = Callable[[Command, 'Context'], list[Element]] # This is here because of a wild circular import dependency between many functions and classes +CommandCallable = Callable[[Command, 'Context', 'NOPProcessor'], list[Element]] # This is here because of a wild circular import dependency between many functions and classes # This class is used to keep state while transforming the document using # transform.py. For the context to be available to the html and TeX generators, @@ -31,11 +30,15 @@ def default_number_generator(e: Header, context: 'Context') -> str: class Context: parent: Union["Context", None] _commands: dict[str, Union[CommandCallable, None]] + _data: dict[str, object] doc: Doc trusted: bool path: str dir: str filename: str + root_dir: str # Absolute path to the dir of the file formátítko was called on + rel_dir: str # Relative path to the current dir from the root dir + deps: set[str] section_counters: list[int] number_generator: Callable[[Header, 'Context'], str] @@ -43,11 +46,16 @@ class Context: def __init__(self, doc: Doc, path: str, parent: Union['Context', None]=None, trusted: bool=True): self.parent = parent self._commands = {} + self._data = {} self.doc = doc self.trusted = trusted self.path = path self.dir = os.path.dirname(path) if os.path.dirname(path) != "" else "." self.filename = os.path.basename(path) + self.root_dir = parent.root_dir if parent else os.path.abspath(self.dir) + self.rel_dir = os.path.relpath(self.dir, self.root_dir) + self.deps = set() + self.add_dep(path) if self.get_metadata("flags", immediate=True) is None: self.set_metadata("flags", {}) self.number_generator = default_number_generator @@ -122,7 +130,57 @@ class Context: else: self.set_metadata(key, data) + def get_data(self, key: str, immediate: bool=False): + data = self._data + keys = key.split(".") + try: + for k in keys: + data = data[k] + return data + except KeyError: + if self.parent and not immediate: + return self.parent.get_data(key) + else: + return None + + def set_data(self, key: str, value: object): + data = self._data + keys = key.split(".") + for k in keys[:-1]: + try: + data = data[k] + except KeyError: + data[k] = {} + data = data[k] + data[keys[-1]] = value + + def unset_data(self, key: str): + if key == "": + self._doc = {} + data = self._doc + keys = key.split(".") + for k in keys[:-1]: + data = data[k] + del data[keys[-1]] + + def get_deps(self) -> list[str]: + if self.parent is not None: + return self.parent.get_deps() + else: + return self.deps + + def add_dep(self, dep: str): + self.get_deps().add(os.path.abspath(dep)) + + def add_deps(self, deps: list[str]): + self.get_deps().update([os.path.abspath(path) for path in deps]) + +def get_context_from_doc(doc: Doc) -> Context: + if len(doc.content) == 1 and isinstance(doc.content[0], Group): + return doc.content[0].context + else: + return None # This is a custom element which creates \begingroup \endgroup groups in TeX # and also causes KaTeX math blocks to be isolated in a similar way. diff --git a/src/formatitko/formatitko.py b/src/formatitko/formatitko.py index 9b3b942..3e764ba 100755 --- a/src/formatitko/formatitko.py +++ b/src/formatitko/formatitko.py @@ -7,18 +7,15 @@ import subprocess import shutil # Import local files -from .transform import transform from .util import import_md -from .context import Context, BlockGroup from .katex import KatexClient -from .html import html -from .tex import tex -from .images import ImageProcessor -from .output_generator import OutputGenerator -from .html_generator import HTMLGenerator +from .images import ImageProcessor, ImageProcessorNamespace +from .output_generator import OutputGenerator, FormatitkoRecursiveError +from .html_generator import HTMLGenerator, StandaloneHTMLGenerator from .transform_processor import TransformProcessor from .pandoc_processor import PandocProcessor from .tex_generator import UCWTexGenerator +from .context import get_context_from_doc from panflute import convert_text @@ -30,6 +27,7 @@ def main(): parser.add_argument("-c", "--img-cache-dir", help="Directory to cache processed images and intermediate products. The program will overwrite files, whose dependencies are newer.", default="cache") parser.add_argument("-i", "--img-web-path", help="Path where the processed images are available on the website.", default="/") parser.add_argument("-w", "--output-html", help="The HTML file (for Web) to write into.") + parser.add_argument("-s", "--output-standalone-html", help="The Standalone HTML file to write into. A full page is generated instead of just a fragment.") parser.add_argument("-t", "--output-tex", help="The TEX file to write into.") parser.add_argument("-m", "--output-md", help="The Markdown file to write into. (Uses pandoc to generate markdown)") parser.add_argument("-j", "--output-json", help="The JSON file to dump the pandoc-compatible AST into.") @@ -38,6 +36,8 @@ def main(): parser.add_argument("-k", "--katex-socket", help="The KaTeX server socket filename obtained by running with `--katex-server`.") parser.add_argument("input_filename", help="The markdown file to process.", nargs="?" if "--katex-server" in sys.argv else None) parser.add_argument("--debug", action='store_true') + parser.add_argument("--traceback-limit", help="Traceback limit for when errors happen, defaults to 0, as it is only useful for internal debugging.", default=0) + parser.add_argument("--deps", help="File to write list of dependencies to. May depend on output formats used.") args = parser.parse_args() if args.katex_server: @@ -54,22 +54,43 @@ def main(): doc = import_md(open(args.input_filename, "r").read()) if args.debug: - OutputGenerator(sys.stdout).generate(doc) + try: + OutputGenerator(sys.stdout).generate(doc) + except FormatitkoRecursiveError as e: + e.pretty_print(tracebacklimit=args.traceback_limit) - doc = TransformProcessor(args.input_filename).transform(doc) + try: + doc = TransformProcessor(args.input_filename).transform(doc) + except FormatitkoRecursiveError as e: + e.pretty_print(tracebacklimit=args.traceback_limit) # Initialize the image processor (this just keeps some basic state) - imageProcessor = ImageProcessor(args.img_public_dir, args.img_web_path, args.img_cache_dir, *args.img_lookup_dirs) + imageProcessor = ImageProcessor({"": ImageProcessorNamespace(args.img_public_dir, args.img_web_path, args.img_cache_dir, args.img_lookup_dirs, True)}) if args.output_html is not None: # Initialize KaTeX client (this runs the node app and connects to a unix socket) with KatexClient(socket=args.katex_socket) as katexClient: with open(args.output_html, "w") as file: - HTMLGenerator(file, katexClient, imageProcessor).generate(doc) + try: + HTMLGenerator(file, katexClient, imageProcessor).generate(doc) + except FormatitkoRecursiveError as e: + e.pretty_print(tracebacklimit=args.traceback_limit) + + if args.output_standalone_html is not None: + # Initialize KaTeX client (this runs the node app and connects to a unix socket) + with KatexClient(socket=args.katex_socket) as katexClient: + with open(args.output_standalone_html, "w") as file: + try: + StandaloneHTMLGenerator(file, katexClient, imageProcessor).generate(doc) + except FormatitkoRecursiveError as e: + e.pretty_print(tracebacklimit=args.traceback_limit) if args.output_tex is not None: with open(args.output_tex, "w") as file: - UCWTexGenerator(file, imageProcessor).generate(doc) + try: + UCWTexGenerator(file, imageProcessor).generate(doc) + except FormatitkoRecursiveError as e: + e.pretty_print(tracebacklimit=args.traceback_limit) if args.output_md is not None: with open(args.output_md, "w") as file: @@ -83,7 +104,10 @@ def main(): if args.output_tex is None: fd = tempfile.NamedTemporaryFile(dir=".", suffix=".tex") with open(fd.name, "w") as file: - UCWTexGenerator(file, imageProcessor).generate(doc) + try: + UCWTexGenerator(file, imageProcessor).generate(doc) + except FormatitkoRecursiveError as e: + e.pretty_print(tracebacklimit=args.traceback_limit) filename = fd.name else: filename = args.output_tex @@ -91,9 +115,17 @@ def main(): subprocess.run(["pdfcsplain", "-halt-on-error", "-output-directory="+outdir.name, "-jobname=formatitko", filename], check=True) shutil.move(outdir.name+"/formatitko.pdf", args.output_pdf) + if args.deps is not None: + with open(args.deps, "w") as file: + for dep in get_context_from_doc(doc).get_deps(): + file.write(dep + "\n") + if args.debug: print("-----------------------------------") - OutputGenerator(sys.stdout).generate(doc) + try: + OutputGenerator(sys.stdout).generate(doc) + except FormatitkoRecursiveError as e: + e.pretty_print(tracebacklimit=args.traceback_limit) if __name__ == "__main__": diff --git a/src/formatitko/html.py b/src/formatitko/html.py deleted file mode 100644 index 0403082..0000000 --- a/src/formatitko/html.py +++ /dev/null @@ -1,311 +0,0 @@ -from panflute import * -from pygments import highlight -from pygments.lexers import get_lexer_by_name -from pygments.formatters import HtmlFormatter -from pygments.util import ClassNotFound -import os -from typing import Union - -from .whitespace import NBSP -from .elements import FQuoted -from .katex import KatexClient -from .util import inlinify -from .context import Group -from .images import ImageProcessor - -import warnings -warnings.warn("The html function has been deprecated, is left only for reference and will be removed in future commits. HTML_generator should be used in its place.", DeprecationWarning) - -def html(e: Union[Element, ListContainer], k: KatexClient, i: ImageProcessor, indent_level: int=0, indent_str: str="\t") -> str: - - warnings.warn("The html function has been deprecated, is left only for reference and will be removed in future commits. HTML_generator should be used in its place.", DeprecationWarning) - - # `only` attribute which makes transformed elements appear only in tex - # output or html output - if hasattr(e, "attributes") and "only" in e.attributes and e.attributes["only"] != "html": - return "" - - if isinstance(e, ListContainer): - return ''.join([html(child, k, i, indent_level, indent_str) for child in e]) - - # Bits from which the final element output is built at the end of this - # function. Most elements override this by returning their own output. - tag = e.tag.lower() - attributes = "" - content_foot = "" - content_head = "" - - if isinstance(e, Str): - return e.text.replace(" ", " ") - - # Most elements fit the general template at the end of the function, just - # need their html tag specified. - tags = { - BulletList: "ul", - Doc: "main", - Emph: "em", - Caption: "figcaption", - Para: "p", - Header: "h"+str(e.level) if isinstance(e, Header) else "", - LineBlock: "p", - ListItem: "li", - SmallCaps: "span", - Strikeout: "strike", - Subscript: "sub", - Superscript: "sup", - Underline: "u", - TableBody: "tbody", - TableHead: "thead", - TableFoot: "tfoot", - TableRow: "tr", - TableCell: "td", - } - if type(e) in tags: - tag = tags[type(e)] - - # These are also disabled in pandoc so they shouldn't appear in the AST at all. - not_implemented = { - Citation: True, - Cite: True, - Definition: True, - DefinitionItem: True, - DefinitionList: True - } - if type(e) in not_implemented: - return f'' - - # Elements which can be represented by a simple string - simple_string = { - NBSP: " ", - Space: " ", - Null: "", - LineBreak: f"\n{indent_level*indent_str}
\n{indent_level*indent_str}", - SoftBreak: f" ", - HorizontalRule: f"{indent_level*indent_str}
\n" - } - if type(e) in simple_string: - return simple_string[type(e)] - - if hasattr(e, "identifier") and e.identifier != "": - attributes += f' id="{e.identifier}"' - - if hasattr(e, "classes") and len(e.classes) != 0: - attributes += f' class="{" ".join(e.classes)}"' - - # Attributes are only passed down manually, because we use them internally. - # Maybe this should be a blocklist instead of an allowlist? - - # Overriding elements with their own returns - if isinstance(e, CodeBlock): - if len(e.classes) > 0 and (e.attributes["highlight"] == True or e.attributes["highlight"] == 'True'): - # Syntax highlighting using pygments - for cl in e.classes: - try: - lexer = get_lexer_by_name(cl) - except ClassNotFound: - continue - break - else: - print(f"WARN: Syntax highligher does not have lexer for element with these classes: {e.classes}") - formatter = HtmlFormatter(style=e.attributes["style"]) - result = highlight(e.text, lexer, formatter) - return f'{result}' - else: - return f'
{e.text}
' - - if isinstance(e, Doc): - formatter = HtmlFormatter(style=e.get_metadata("highlight-style") if e.get_metadata("highlight-style") is not None else "default") - content_head = f'' - - if isinstance(e, Image): - url = e.url - - # Attributes → image processor args - additional_args = {} - if "file-width" in e.attributes: - additional_args["width"] = int(e.attributes["file-width"]) - if "file-height" in e.attributes: - additional_args["height"] = int(e.attributes["file-height"]) - if "file-quality" in e.attributes: - additional_args["quality"] = int(e.attributes["file-quality"]) - if "file-dpi" in e.attributes: - additional_args["dpi"] = int(e.attributes["file-dpi"]) - - # The directory of the current file, will also look for images there. - source_dir = e.attributes["source_dir"] - - _, ext = os.path.splitext(url) - ext = ext[1:] - - # Conversions between various formats. - if ext in ["svg", "png", "jpeg", "gif"]: - # Even supported elements have to be 'converted' because the - # processing contains finding and moving them to the output - # directory. - url = i.process_image(url, ext, source_dir, **additional_args) - elif ext in ["pdf", "epdf"]: - if not "dpi" in additional_args: - additional_args["dpi"] = 300 - url = i.process_image(url, "png", source_dir, **additional_args) - elif ext in ["jpg"]: - url = i.process_image(url, "jpeg", source_dir, **additional_args) - else: - url = i.process_image(url, "png", source_dir, **additional_args) - - # Srcset generation - multiple alternative sizes of images browsers can - # choose from. - _, ext = os.path.splitext(url) - ext = ext[1:] - srcset = [] - if ext in ["png", "jpeg"] and (not "no-srcset" in e.attributes or e.attributes["no-srcset"] == False or e.attributes["no-srcset"] == 'False'): - # This is inspired by @vojta001's blogPhoto shortcode he made for - # patek.cz: - # https://gitlab.com/patek-devs/patek.cz/-/blob/master/themes/patek/layouts/shortcodes/blogPhoto.html - width, height = i.get_image_size(url, [i.public_dir]) - sizes = [(640, 360, 85), (1280, 720, 85), (1920, 1080, 90)] # (widht, height, quality) - for size in sizes: - if width <= size[0] and height <= size[1]: - srcset.append((f'{i.web_path}/{url}', f'{width}w')) - break - quality = size[2] if ext == "jpeg" else None - srcset.append((f'{i.web_path}/{i.process_image(url, ext, i.public_dir, width=size[0], height=size[1], quality=quality)}', f'{size[0]}w')) - - url = i.web_path + "/" + url - - attributes = f'{" style=width:"+e.attributes["width"] if "width" in e.attributes else ""} alt="{e.title or html(e.content, k, i, 0, "")}"' - if len(srcset) != 0: - return f'' - else: - return f'' - - # See https://pandoc.org/MANUAL.html#line-blocks - if isinstance(e, LineItem): - return indent_level*indent_str + html(e.content, k, i) + "
\n" - - # Footnotes are placed into parentheses. (And not footnotes (This is how KSP did it before me)) - if isinstance(e, Note): - content_head = "(" - content_foot = ")" - if inlinify(e) is not None: - return f' ({html(inlinify(e), k, i, 0, "")})' - - if isinstance(e, FQuoted): - if e.style == "cs": - if e.quote_type == "SingleQuote": - return f'‚{html(e.content, k, i, 0, "")}‘' - elif e.quote_type == "DoubleQuote": - return f'„{html(e.content, k, i, 0, "")}“' - elif e.style == "en": - if e.quote_type == "SingleQuote": - return f'‘{html(e.content, k, i, 0, "")}’' - elif e.quote_type == "DoubleQuote": - return f'“{html(e.content, k, i, 0, "")}”' - else: - if e.quote_type == "SingleQuote": - return f'\'{html(e.content, k, i, 0, "")}\'' - elif e.quote_type == "DoubleQuote": - return f'"{html(e.content, k, i, 0, "")}"' - else: - return f'"{html(e.content, k, i, 0, "")}"' - - if isinstance(e, Group): - k.begingroup() - ret = html(e.content, k, i, indent_level, indent_str) - k.endgroup() - return ret - - if isinstance(e, Math): - formats = { - "DisplayMath": True, - "InlineMath": False - } - return indent_level*indent_str + k.render(e.text, {"displayMode": formats[e.format]}) - - if isinstance(e, RawInline): - if e.format == "html": - return e.text - else: - return "" - - if isinstance(e, RawBlock): - if e.format == "html": - return f'{e.text}\n' - else: - return "" - - - # Non-overriding elements, they get generated using the template at the end - # of this function - if isinstance(e, Header): - tag = "h"+str(e.level) - - if isinstance(e, Figure): - content_foot = html(e.caption, k, i, indent_level+1, indent_str) - - if isinstance(e, Caption): - tag = "figcaption" - - if isinstance(e, Link): - tag = "a" - attributes += f' href="{e.url}"' - if e.title: - attributes += f' title="{e.title}"' - - if isinstance(e, OrderedList): - tag = "ol" - if e.start and e.start != 1: - attributes += f' start="{e.start}"' - html_styles = { - "Decimal": "1", - "LowerRoman": "i", - "UpperRoman:": "I", - "LowerAlpha": "a", - "UpperAlpha": "A" - } - if e.style and e.style != "DefaultStyle": - attributes += f' type="{html_styles[e.style]}"' - # FIXME: Delimeter styles - - if isinstance(e, Table): - content_head = html(e.head, k, i, indent_level+1, indent_str) - content_foot = html(e.foot, k, i, indent_level+1, indent_str) - # FIXME: Fancy pandoc tables, using colspec - - if isinstance(e, TableCell): - tag = "td" - if e.colspan != 1: - attributes += f' colspan="{e.colspan}"' - if e.rowspan != 1: - attributes += f' rowspan="{e.rowspan}"' - aligns = { - "AlignLeft": "left", - "AlignRight": "right", - "AlignCenter": "center" - } - if e.alignment and e.alignment != "AlignDefault": - attributes += f' style="text-align: {aligns[e.alignment]}"' - - # The default which all non-overriding elements get generated by. This - # includes elements, which were not explicitly mentioned in this function, - # e. g. Strong - - if isinstance(e, Inline): - return f'<{tag}{attributes}>{content_head}{html(e.content, k, i, 0, "") if hasattr(e, "_content") else ""}{e.text if hasattr(e, "text") else ""}{content_foot}' - - out_str = "" - if not isinstance(e, Plain): - out_str += f"{indent_level*indent_str}<{tag}{attributes}>\n" - out_str += content_head - if hasattr(e, "_content"): - if len(e.content) > 0 and isinstance(e.content[0], Inline): - out_str += (indent_level+1)*indent_str - out_str += html(e.content, k, i, indent_level+1, indent_str) - if hasattr(e, "text"): - out_str += e.text - out_str += f"{content_foot}\n" - if not isinstance(e, Plain): - out_str += f"{indent_level*indent_str}\n" - - return out_str - - diff --git a/src/formatitko/html_generator.py b/src/formatitko/html_generator.py index d564044..2aabe85 100644 --- a/src/formatitko/html_generator.py +++ b/src/formatitko/html_generator.py @@ -17,9 +17,10 @@ from .whitespace import NBSP from .context import Group, BlockGroup, InlineGroup from .output_generator import OutputGenerator from .katex import KatexClient -from .images import ImageProcessor +from .images import ImageProcessor, ImageProcessorNamespaceSearcher from .util import inlinify + class HTMLGenerator(OutputGenerator): imageProcessor: ImageProcessor katexClient: KatexClient @@ -136,9 +137,15 @@ class HTMLGenerator(OutputGenerator): url = e.url additional_args = self.get_image_processor_args(e.attributes) + additional_args["context"] = self.context - # The directory of the current file, will also look for images there. + # The directory of the current file relative to the current working directory source_dir = self.context.dir + # The directory of the current file relative to the md file we were called on + rel_dir = self.context.rel_dir + + searcher = self.imageProcessor.get_searcher_by_path(url, rel_dir, source_dir) + url = self.imageProcessor.get_path_without_namespace(url) _, ext = os.path.splitext(url) ext = ext[1:] @@ -148,16 +155,16 @@ class HTMLGenerator(OutputGenerator): # Even supported elements have to be 'converted' because the # processing contains finding and moving them to the output # directory. - url = self.imageProcessor.process_image(url, ext, source_dir, **additional_args) + url = self.imageProcessor.process_image(url, ext, searcher, **additional_args) elif ext in ["pdf", "epdf","asy"]: # Only relevant for when these were PNGs, leaving this here for future reference. # if not "dpi" in additional_args: # additional_args["dpi"] = 300 - url = self.imageProcessor.process_image(url, "svg", source_dir, **additional_args) + url = self.imageProcessor.process_image(url, "svg", searcher, **additional_args) elif ext in ["jpg"]: - url = self.imageProcessor.process_image(url, "jpeg", source_dir, **additional_args) + url = self.imageProcessor.process_image(url, "jpeg", searcher, **additional_args) else: - url = self.imageProcessor.process_image(url, "png", source_dir, **additional_args) + url = self.imageProcessor.process_image(url, "png", searcher, **additional_args) # Srcset generation - multiple alternative sizes of images browsers can # choose from. @@ -168,23 +175,25 @@ class HTMLGenerator(OutputGenerator): # This is inspired by @vojta001's blogPhoto shortcode he made for # patek.cz: # https://gitlab.com/patek-devs/patek.cz/-/blob/master/themes/patek/layouts/shortcodes/blogPhoto.html - width, height = self.imageProcessor.get_image_size(url, [self.imageProcessor.cache_dir]) + width, height = self.imageProcessor.get_image_size(searcher.find_image_in_dir(url, searcher.get_cache_dir())) sizes = [(640, 360, 85), (1280, 720, 85), (1920, 1080, 90)] # (widht, height, quality) for size in sizes: if width <= size[0] and height <= size[1]: - srcset.append((f'{self.imageProcessor.web_path}/{url}', f'{width}w')) + srcset.append((f'{searcher.get_web_path()}/{url}', f'{width}w')) break quality = size[2] if ext == "jpeg" else None - cache_img = self.imageProcessor.process_image(url, ext, self.imageProcessor.cache_dir, width=size[0], height=size[1], quality=quality) - self.imageProcessor.publish_image(cache_img) - srcset.append((f'{self.imageProcessor.web_path}/{cache_img}', f'{size[0]}w')) + cache_img = self.imageProcessor.process_image(url, ext, searcher.get_cache_searcher(), width=size[0], height=size[1], quality=quality) + searcher.publish_image(cache_img) + srcset.append((f'{searcher.get_web_path()}/{cache_img}', f'{size[0]}w')) - self.imageProcessor.publish_image(url) - url = self.imageProcessor.web_path + "/" + url + searcher.publish_image(url) + url = searcher.get_web_path() + "/" + url attributes = self.common_attributes(e) if "width" in e.attributes: attributes["width"] = e.attributes["width"] + if "height" in e.attributes: + attributes["height"] = e.attributes["height"] if e.title: attributes["alt"] = e.title @@ -199,6 +208,10 @@ class HTMLGenerator(OutputGenerator): else: attributes["src"] = url + if e.attributes["no-img-link"]: + self.write(self.single_tag("img", attributes)) + return + img = RawInline(self.single_tag("img", attributes)) link = Link(img, url=url) @@ -310,3 +323,34 @@ class HTMLGenerator(OutputGenerator): def generate_DefinitionList(self, e: DefinitionList): self.writeln("") + + +class StandaloneHTMLGenerator(HTMLGenerator): + def generate_Doc(self, e: Doc): + self.writeraw("") + self.writeln(self.start_tag("html", attributes={"lang": e.get_metadata("lang", None, True)})) + self.writeln(self.start_tag("head")) + self.indent_more() + self.writeln(self.single_tag("meta", attributes={"charset": "utf-8"})) + self.writeln(self.single_tag("meta", attributes={"viewport": "width=device-width, initial-scale=1.0"})) + self.writeln(self.single_tag("link", attributes={"rel": "stylesheet", "href": "https://cdn.jsdelivr.net/npm/katex@0.16.4/dist/katex.min.css", "integrity":"sha384-vKruj+a13U8yHIkAyGgK1J3ArTLzrFGBbBc0tDp4ad/EyewESeXE/Iv67Aj8gKZ0", "crossorigin":"anonymous"})) + if "title" in e.metadata: + self.write(self.start_tag("title")) + self.generate(e.metadata["title"]) + self.write(self.end_tag("title")) + self.endln() + if "html-head-includes" in e.metadata: + self.generate(e.metadata["html-head-includes"]) + self.indent_less() + self.writeln(self.end_tag("head")) + self.writeln(self.start_tag("body")) + self.indent_more() + super().generate_Doc(e) + self.indent_less() + self.writeln(self.end_tag("body")) + self.writeln(self.end_tag("html")) + + + + + diff --git a/src/formatitko/images.py b/src/formatitko/images.py index 73220dc..c447c30 100644 --- a/src/formatitko/images.py +++ b/src/formatitko/images.py @@ -4,46 +4,171 @@ import shutil import subprocess from PIL import Image +from .context import Context + + class FileInWrongDirError(Exception): pass + class ConversionProgramError(Exception): pass + class InkscapeError(ConversionProgramError): pass + class ImageMagickError(ConversionProgramError): pass + class AsyError(ConversionProgramError): pass - -class ImageProcessor: +class ImageProcessorNamespace: public_dir: str cache_dir: str lookup_dirs: list[str] web_path: str + include_src: bool - def __init__(self, public_dir: str, web_path: str, cache_dir: str, *lookup_dirs: list[str]): + def __init__(self, public_dir: str, web_path: str, cache_dir: str, lookup_dirs: list[str], include_src: bool): self.public_dir = public_dir self.cache_dir = cache_dir self.lookup_dirs = lookup_dirs self.web_path = web_path if web_path[-1] != "/" else web_path[:-1] - if not os.path.exists(self.public_dir): - os.mkdir(self.public_dir) + self.include_src = include_src + +class ImageProcessorSearcher: + def get_lookup_dirs(self) -> list[str]: + return [] + + def get_cache_dir(self) -> str: + return "" + + def get_public_dir(self) -> str: + return "" + + def get_web_path(self) -> str: + return "" + + def find_image_in_dir(self, input_filename: str, dir: str) -> Union[str, None]: + if os.path.isfile(dir + "/" + input_filename): + return dir + "/" + input_filename + else: + return None + + def find_image(self, input_filename: str) -> Union[str, None]: + for dir in self.get_lookup_dirs(): + image = self.find_image_in_dir(input_filename, dir) + if image: + return image + return None + + def publish_image(self, target_name, relative: bool=True) -> str: + cache_path = self.get_cache_dir() + "/" + target_name + if not os.path.isfile(cache_path): + raise FileNotFoundError(f'Image {target_name} not cached') + target_path = self.get_public_dir() + "/" + target_name + try: + if os.path.exists(target_path): + if os.path.getmtime(cache_path) > os.path.getmtime(target_path): + os.remove(target_path) + os.link(cache_path, target_path) + else: + os.link(cache_path, target_path) + except OSError as e: + if e.errno == 18: # Invalid cross-device link: cache and public dirs are on different devices, don't hardlink, copy + shutil.copyfile(cache_path, target_path) + else: + raise e + return target_name if relative else target_path + + + +class ImageProcessorCacheSearcher(ImageProcessorSearcher): + cache_dir: str + + def __init__(self, cache_dir: str): + self.cache_dir = cache_dir if not os.path.exists(self.cache_dir): - os.mkdir(self.cache_dir) + os.makedirs(self.cache_dir, exist_ok=True) + + def get_lookup_dirs(self) -> list[str]: + return [self.cache_dir] + + def get_cache_dir(self) -> str: + return self.cache_dir + + def get_public_dir(self) -> str: + return "" - def process_image(self, input_filename: str, format: str, source_dir: str, width: int=None, height:int=None, quality: int=None, dpi: int=None, fit: bool=True, deps: list[str]=[]) -> str: + def get_web_path(self) -> str: + return "" + + def publish_image(self, target_name, relative: bool=True) -> str: + raise NotImplementedError(); + +class ImageProcessorNamespaceSearcher(ImageProcessorSearcher): + namespace: ImageProcessorNamespace + rel_dir: str + source_dir: str + + def __init__(self, namespace: ImageProcessorNamespace, rel_dir: str, source_dir: str): + self.namespace = namespace + self.rel_dir = rel_dir + self.source_dir = source_dir + + def get_lookup_dirs(self) -> list[str]: + return self.namespace.lookup_dirs + ([self.source_dir] if self.namespace.include_src else []) + + def transform_path(self, path: str) -> str: + return path.replace("$dir", self.rel_dir) + + def get_cache_dir(self) -> str: + cache_dir = self.transform_path(self.namespace.cache_dir) + if not os.path.exists(cache_dir): + os.makedirs(cache_dir, exist_ok=True) + return cache_dir + + def get_public_dir(self) -> str: + public_dir = self.transform_path(self.namespace.public_dir) + if not os.path.exists(public_dir): + os.makedirs(public_dir, exist_ok=True) + return public_dir + + def get_web_path(self) -> str: + return self.transform_path(self.namespace.web_path) + + def get_cache_searcher(self) -> ImageProcessorCacheSearcher: + return ImageProcessorCacheSearcher(self.get_cache_dir()) + +class ImageProcessor: + namespaces: dict[str, ImageProcessorNamespace] + + def __init__(self, namespaces: dict[str, ImageProcessorNamespace]): + self.namespaces = namespaces + + def get_namespace_by_path(self, path: str) -> ImageProcessorNamespace: + return self.namespaces[path.split(":")[0] if ":" in path else ""] + + def get_path_without_namespace(self, path: str) -> str: + if len(path.split(":")) <= 1: + return path + return ":".join(path.split(":")[1:]) + + def get_searcher_by_path(self, path: str, rel_dir: str, source_dir: str) -> ImageProcessorNamespaceSearcher: + return ImageProcessorNamespaceSearcher(self.get_namespace_by_path(path), rel_dir, source_dir) + + def process_image(self, input_filename: str, format: str, searcher: ImageProcessorSearcher, context: Context=None, width: int=None, height:int=None, quality: int=None, dpi: int=None, fit: bool=True, deps: list[str]=[]) -> str: name = os.path.basename(input_filename) base, ext = os.path.splitext(name) ext = ext[1:] - full_path = self.find_image(input_filename, [source_dir]) + full_path = searcher.find_image(input_filename) if full_path is None: - raise FileNotFoundError(f'Image {input_filename} not found in {self.lookup_dirs} or {source_dir}.') + raise FileNotFoundError(f'Image {input_filename} not found in {searcher.get_lookup_dirs()}.') if format == "jpg": format = "jpeg" @@ -51,7 +176,7 @@ class ImageProcessor: # Locate all dependencies deps_full = [full_path] for dep in deps: - dep_full_path = self.find_image(dep, [source_dir]) + dep_full_path = searcher.find_image(dep) if dep_full_path is None: raise FileNotFoundError(f'Image dependency {dep} not found.') deps_full.append(dep_full_path) @@ -65,7 +190,7 @@ class ImageProcessor: if quality is not None: suffix += f'_q{quality}' target_name = base+suffix+"."+format - target_path = self.cache_dir + "/" + target_name + target_path = searcher.get_cache_dir() + "/" + target_name # Only regenerate if the file doesn't already exist and no dependencies are newer if not os.path.isfile(target_path) or self.is_outdated(target_path, deps_full): @@ -80,13 +205,13 @@ class ImageProcessor: # Try to find the converted filename in lookup_dirs, if you find # it, don't convert, just copy. - elif self.find_image(target_name, [source_dir]) is not None and not self.is_outdated(self.find_image(target_name, [source_dir]), deps): - shutil.copyfile(self.find_image(target_name, [source_dir]), target_path) + elif searcher.find_image(target_name) is not None and not self.is_outdated(searcher.find_image(target_name), deps): + shutil.copyfile(searcher.find_image(target_name), target_path) # Process asymptote elif ext == "asy": # Collect dependencies - deps_dir = self.cache_dir + "/" + name + "_deps" + deps_dir = searcher.get_cache_dir() + "/" + name + "_deps" if not os.path.isdir(deps_dir): os.mkdir(deps_dir) for dep_full in deps_full: @@ -96,7 +221,7 @@ class ImageProcessor: dpi_arg = ['-render', str(dpi/72)] if dpi is not None else [] if subprocess.run(['asy', name, '-o', target_name, '-f', format, *dpi_arg], cwd=deps_dir).returncode != 0: raise AsyError(f"Could not convert '{full_path}' to '{format}'") - shutil.move(deps_dir + "/" + target_name, self.cache_dir + "/" + target_name) + shutil.move(deps_dir + "/" + target_name, searcher.get_cache_dir() + "/" + target_name) # Convert SVGs using inkscape elif ext == "svg": @@ -114,6 +239,8 @@ class ImageProcessor: if subprocess.run(['convert', *density_arg, full_path, *resize_arg, *quality_arg, target_path]).returncode != 0: raise ImageMagickError(f"Could not convert '{full_path}' to '{format}'") + if context is not None: + context.add_deps(deps_full) return target_name def is_outdated(self, target: str, deps: list[str]): @@ -124,37 +251,7 @@ class ImageProcessor: return True return False - def publish_image(self, target_name, relative: bool=True) -> str: - cache_path = self.cache_dir + "/" + target_name - if not os.path.isfile(cache_path): - raise FileNotFoundError(f'Image {target_name} not cached') - target_path = self.public_dir + "/" + target_name - try: - if os.path.exists(target_path): - if os.path.getmtime(cache_path) > os.path.getmtime(target_path): - os.remove(target_path) - os.link(cache_path, target_path) - else: - os.link(cache_path, target_path) - except OSError as e: - if e.errno == 18: # Invalid cross-device link: cache and public dirs are on different devices, don't hardlink, copy - shutil.copyfile(cache_path, target_path) - else: - raise e - return target_name if relative else target_path - - def get_image_size(self, input_filename: str, additional_dirs: list[str]=[]) -> tuple[int, int]: - full_path = self.find_image(input_filename, additional_dirs) - if full_path is None: - raise FileNotFoundError(f'Image {input_filename} not found.') + def get_image_size(self, full_path: str) -> tuple[int, int]: # Getting image size using ImageMagick is slow. VERY return Image.open(full_path).size - - def find_image(self, input_filename: str, additional_dirs: list[str]=[]) -> Union[str, None]: - for dir in [*self.lookup_dirs, *additional_dirs]: - if os.path.isfile(dir + "/" + input_filename): - return dir + "/" + input_filename - - - diff --git a/src/formatitko/katex-server b/src/formatitko/katex-server new file mode 160000 index 0000000..953b44e --- /dev/null +++ b/src/formatitko/katex-server @@ -0,0 +1 @@ +Subproject commit 953b44e942282375ac369af233c123b28146713e diff --git a/src/formatitko/katex-server/.gitignore b/src/formatitko/katex-server/.gitignore deleted file mode 100644 index 3c3629e..0000000 --- a/src/formatitko/katex-server/.gitignore +++ /dev/null @@ -1 +0,0 @@ -node_modules diff --git a/src/formatitko/katex-server/README.md b/src/formatitko/katex-server/README.md deleted file mode 100644 index 082cd55..0000000 --- a/src/formatitko/katex-server/README.md +++ /dev/null @@ -1 +0,0 @@ -This was made by Standa Lukeš @exyi diff --git a/src/formatitko/katex-server/index.js b/src/formatitko/katex-server/index.js deleted file mode 100644 index d6754c8..0000000 --- a/src/formatitko/katex-server/index.js +++ /dev/null @@ -1 +0,0 @@ -console.log(require('katex').renderToString('\\frac{2a}{b}')) diff --git a/src/formatitko/katex-server/index.mjs b/src/formatitko/katex-server/index.mjs deleted file mode 100644 index 2c1c05c..0000000 --- a/src/formatitko/katex-server/index.mjs +++ /dev/null @@ -1,131 +0,0 @@ -// KaTeX rendering server -// Listens on unix socket, path is provided as first argument -// Expects JSON lines, each line is a query with the following schema: -// { -// formulas: [ -// { -// tex: string, -// options?: object -// } -// ], -// options?: object -// } - -// see https://katex.org/docs/options.html for list of available options -// If options formulas[].options field is used, the global options field is ignored. - -// For each line, returns one JSON line with the following schema: -// { -// results: [ -// { html?: string } | { error?: string } -// ] -// } | { error?: string } - - -// If one formula is invalid, the error in results is used -// If the entire query is invalid (couldn't parse JSON, for example), the outer error field is used - - -import katex from 'katex' -import net from 'net' -import * as readline from 'readline' - -const myArgs = process.argv.slice(2) - -const unixSocketPath = myArgs[0] -if (!unixSocketPath) { - console.error('you must specify socket path') - process.exit(1) -} - -// This server listens on a Unix socket at /var/run/mysocket -var unixServer = net.createServer(handleClient); -unixServer.listen(unixSocketPath); -console.log("OK") - -function handleExit(signal) { - // unixServer.emit('close') - unixServer.close(function () { - - }); - process.exit(0); // put this into the callback to avoid closing open connections -} -process.on('SIGINT', handleExit); -process.on('SIGQUIT', handleExit); -process.on('SIGTERM', handleExit); -process.on('exit', handleExit); - -const defaultOptions = {} - -/** - * @param {net.Socket} socket - * @returns {Promise} - * */ -function socketWrite(socket, data) { - return new Promise((resolve, reject) => { - socket.write(data, (err) => { - if (err) { - reject(err) - } else { - resolve() - } - }) - }) -} - -/** - * @param {net.Socket} client - * */ -async function handleClient(client) { - const rl = readline.createInterface({ input: client }) - - /* Added by GS: A stack of katex's `macros` objects, each group inherits - * the one from the parent group and can add its own stuff without - * affecting the parent. - */ - let macroStack = [{}] - for await (const line of rl) { - try { - // The custom commands for pushing and popping the macro stack. - if (line === "begingroup") { - // Copy the current state of macros and push it onto the stack. - macroStack.push({...macroStack.slice(-1)[0]}) - continue - } else if (line === "endgroup") { - macroStack.pop() - continue - } else if (line === "init") { - macroStack = [{}] - continue - } - const query = JSON.parse(line) - const results = [] - for (const input of query.formulas) { - const options = input.options ?? query.options ?? defaultOptions - // Add macros from the macros option - if (options.macros) { - for (const macro of Object.keys(options.macros)) { - macroStack.slice(-1)[macro] = options.macros[macro] - } - } - options.macros = macroStack.slice(-1)[0] - // Enforce globalGroup option, katex then saves created macros - // into the options.macros object. - options.globalGroup = true - try { - const html = katex.renderToString(input.tex, options) - results.push({ html }) - } catch (e) { - results.push({ error: String(e) }) - } - } - await socketWrite(client, JSON.stringify({ results }, null, query.debug ? ' ' : undefined)) - await socketWrite(client, '\n') - } catch (e) { - console.error(e) - await socketWrite(client, JSON.stringify({ error: String(e) })) - await socketWrite(client, '\n') - } - } -} - diff --git a/src/formatitko/katex-server/package-lock.json b/src/formatitko/katex-server/package-lock.json deleted file mode 100644 index 3b5bee3..0000000 --- a/src/formatitko/katex-server/package-lock.json +++ /dev/null @@ -1,39 +0,0 @@ -{ - "name": "ksp-katex-server", - "version": "1.0.0", - "lockfileVersion": 3, - "requires": true, - "packages": { - "": { - "name": "ksp-katex-server", - "version": "1.0.0", - "license": "ISC", - "dependencies": { - "katex": "^0.16.3" - } - }, - "node_modules/commander": { - "version": "8.3.0", - "resolved": "https://registry.npmjs.org/commander/-/commander-8.3.0.tgz", - "integrity": "sha512-OkTL9umf+He2DZkUq8f8J9of7yL6RJKI24dVITBmNfZBmri9zYZQrKkuXiKhyfPSu8tUhnVBB1iKXevvnlR4Ww==", - "engines": { - "node": ">= 12" - } - }, - "node_modules/katex": { - "version": "0.16.3", - "resolved": "https://registry.npmjs.org/katex/-/katex-0.16.3.tgz", - "integrity": "sha512-3EykQddareoRmbtNiNEDgl3IGjryyrp2eg/25fHDEnlHymIDi33bptkMv6K4EOC2LZCybLW/ZkEo6Le+EM9pmA==", - "funding": [ - "https://opencollective.com/katex", - "https://github.com/sponsors/katex" - ], - "dependencies": { - "commander": "^8.0.0" - }, - "bin": { - "katex": "cli.js" - } - } - } -} diff --git a/src/formatitko/katex-server/package.json b/src/formatitko/katex-server/package.json deleted file mode 100644 index 3d68121..0000000 --- a/src/formatitko/katex-server/package.json +++ /dev/null @@ -1,14 +0,0 @@ -{ - "name": "ksp-katex-server", - "version": "1.0.0", - "description": "", - "main": "index.mjs", - "scripts": { - "test": "echo \"Error: no test specified\" && exit 1" - }, - "author": "", - "license": "ISC", - "dependencies": { - "katex": "^0.16.3" - } -} diff --git a/src/formatitko/katex.py b/src/formatitko/katex.py index ad431e6..f81db24 100644 --- a/src/formatitko/katex.py +++ b/src/formatitko/katex.py @@ -3,6 +3,7 @@ import subprocess import tempfile import json import os +import shutil class KatexError(Exception): pass @@ -20,8 +21,10 @@ class KatexClient: _socket_file: str _temp_dir: tempfile.TemporaryDirectory[str] _connected: bool + _katex_server_path: str - def __init__(self, socket: str=None, connect: bool=True): + def __init__(self, socket: str=None, connect: bool=True, katex_server_path: str=None): + self._katex_server_path = katex_server_path if socket is not None: self._socket_file = socket else: @@ -38,20 +41,21 @@ class KatexClient: self._temp_dir = tempfile.TemporaryDirectory(prefix='formatitko') self._socket_file = self._temp_dir.name + "/katex-socket" - srcdir = os.path.dirname(os.path.realpath(__file__)) + if self._katex_server_path is None: + + srcdir = os.path.dirname(os.path.realpath(__file__)) - # Test if `node_modules` directory exists and if not, run `npm install` - if not os.path.isdir(srcdir + "/katex-server/node_modules"): - print("Installing node dependencies for the first time...") - try: - subprocess.run(["npm", "install"], cwd=srcdir+"/katex-server", check=True) - except subprocess.CalledProcessError as e: - if e.returncode == 127: + # Test if `node_modules` directory exists and if not, run `npm install` + if not os.path.isdir(srcdir + "/katex-server/node_modules"): + print("Installing node dependencies for the first time...") + npm = shutil.which("npm") or shutil.which("yarnpkg") + if npm is None: raise NPMNotFoundError("npm not found. Node.js is required to use KaTeX.") - else: - raise e + subprocess.run([npm, "install"], cwd=srcdir+"/katex-server", check=True) + + self._katex_server_path = srcdir + "/katex-server/index.mjs" - self._server_process = subprocess.Popen(["node", srcdir + "/katex-server/index.mjs", self._socket_file], stdout=subprocess.PIPE) + self._server_process = subprocess.Popen(["node", self._katex_server_path, self._socket_file], stdout=subprocess.PIPE) ok = self._server_process.stdout.readline() if ok != b"OK\n": @@ -79,7 +83,7 @@ class KatexClient: if "error" in response: raise KatexServerError(response["error"]) if "error" in response["results"][0]: - raise KatexError(response["results"][0]["error"]) + raise KatexError(response["results"][0]["error"] + " in $" + tex + "$") else: return response["results"][0]["html"] diff --git a/src/formatitko/nop_processor.py b/src/formatitko/nop_processor.py index 2f09ffb..8218b2e 100644 --- a/src/formatitko/nop_processor.py +++ b/src/formatitko/nop_processor.py @@ -7,15 +7,20 @@ from typing import Union, Callable from .whitespace import NBSP from .elements import FQuoted -from .context import Group, InlineGroup, BlockGroup +from .context import Group, InlineGroup, BlockGroup, Context from .whitespace import Whitespace from .command import BlockCommand, InlineCommand, CodeCommand, Command +from .output_generator import FormatitkoRecursiveError ELCl = Union[Element, ListContainer, list[Union[Element, ListContainer]]] +class DoubleDocError(Exception): + "TransformProcessor should only ever see a single Doc." + pass class NOPProcessor: TYPE_DICT: dict[type, Callable] + context: Union[Context, None] = None class UnknownElementError(Exception): f"An unknown Element has been passed to the NOPProcessor, probably because panflute introduced a new one." @@ -96,32 +101,45 @@ class NOPProcessor: return [] def transform(self, e: ELCl) -> ELCl: - if isinstance(e, list): - return self.transform_list(e) - elif isinstance(e, ListContainer): - return self.transform_ListContainer(e) + try: + if isinstance(e, list): + return self.transform_list(e) + elif isinstance(e, ListContainer): + return self.transform_ListContainer(e) - for transformer in self.get_pretransformers(): - e = transformer(e) + for transformer in self.get_pretransformers(): + e = transformer(e) - try: - e = self.TYPE_DICT[type(e)](e) - except KeyError: - raise self.UnknownElementError(type(e)) + try: + method = self.TYPE_DICT[type(e)] + except KeyError: + raise self.UnknownElementError(type(e)) - for transformer in self.get_posttransformers(): - e = transformer(e) + e = method(e) - return e + for transformer in self.get_posttransformers(): + e = transformer(e) + + return e + except FormatitkoRecursiveError as err: + if not isinstance(e, ListContainer): + err.add_element(e) + raise err + except Exception as err: + raise FormatitkoRecursiveError(e, self.context) from err def transform_list(self, e: list[Union[Element, ListContainer]]) -> list[Union[Element, ListContainer]]: - for i in range(len(e)): + i = 0 + while i < len(e): # The length of the list can change mid-transformation, so we need to check the length each time e[i] = self.transform(e[i]) + i-=-1 return e def transform_ListContainer(self, e: ListContainer) -> ListContainer: - for i in range(len(e)): + i = 0 + while i < len(e): # The length of the list can change mid-transformation, so we need to check the length each time e[i] = self.transform(e[i]) + i-=-1 return e @@ -293,6 +311,9 @@ class NOPProcessor: return e def transform_Doc(self, e: Doc) -> Doc: + if self.context is not None: + raise DoubleDocError() + self.context = Context(e, self.root_file_path) e.content = self.transform(e.content) return e diff --git a/src/formatitko/output_generator.py b/src/formatitko/output_generator.py index 61df1c6..8e854a3 100644 --- a/src/formatitko/output_generator.py +++ b/src/formatitko/output_generator.py @@ -3,18 +3,56 @@ from panflute import Cite, Code, Emph, Image, LineBreak, Link, Math, Note, Quote from panflute import BlockQuote, BulletList, Citation, CodeBlock, Definition, DefinitionItem, DefinitionList, Div, Figure, Header, HorizontalRule, LineBlock, LineItem, ListItem, MetaBlocks, MetaBool, MetaInlines, MetaList, MetaMap, MetaString, Null, OrderedList, Para, Plain, RawBlock, Table, TableBody, TableFoot, TableHead from panflute import TableRow, TableCell, Caption, Doc from panflute import MetaValue +from panflute import stringify from typing import Union, Callable from .whitespace import NBSP from .elements import FQuoted from .context import Group, InlineGroup, BlockGroup, Context -import re + +import sys class UnknownElementError(Exception): "An unknown Element has been passed to the OutputGenerator, probably because panflute introduced a new one." pass + +class FormatitkoRecursiveError(Exception): + "A generic exception which wraps other exceptions and adds element-based traceback" + elements: list[Union[Element, ListContainer, list[Union[Element, ListContainer]]]] + context: Context + + def __init__(self, e: Union[Element, ListContainer, list[Union[Element, ListContainer]]], context: Context, *args): + self.elements = [e] + self.context = context + super().__init__(args) + + def add_element(self, e: Union[Element, ListContainer, list[Union[Element, ListContainer]]]): + self.elements.append(e) + + def pretty_print(self, tracebacklimit: int=0): + def eprint(*args, **kwargs): + print(*args, file=sys.stderr, **kwargs) + + def print_filename_recursive(context: Context): + return context.path +\ + ((" (included from " + print_filename_recursive(context.parent) + ")") if context.parent else "") + eprint(f"Error occured in file {print_filename_recursive(self.context)} in ", end="") + line = None + for i in range(len(self.elements)-1, 0, -1): + if hasattr(self.elements[i], "content") and len(self.elements[i].content) > 0 and isinstance(self.elements[i].content[0], Inline) and line is None: + line = self.elements[i] + eprint(type(self.elements[i]).__name__ + "[" + (str(self.elements[i-1].index) if isinstance(self.elements[i-1].index, int) else "") + "]", end=": ") + if line: + eprint() + eprint('on line: "' + stringify(line).strip() + '"', end="") + eprint() + eprint("in element: " + str(self.elements[0]).replace("\n", "\\n")) + sys.tracebacklimit = tracebacklimit + raise self.__cause__ from None + + class OutputGenerator: _empty_lines: int context: Union[Context, None] @@ -101,28 +139,36 @@ class OutputGenerator: } def generate(self, e: Union[Element, ListContainer, list[Union[Element, ListContainer]]]): - if isinstance(e, Group): - old_context = self.context - self.context = e.context - if isinstance(e, list): - self.generate_list(e) - elif isinstance(e, ListContainer): - self.generate_ListContainer(e) - elif isinstance(e, Inline): - self.generate_Inline(e) - elif isinstance(e, Block): - self.generate_Block(e) - elif isinstance(e, MetaValue): - self.generate_MetaValue(e) - elif isinstance(e, MetaList): - self.generate_MetaList(e) - else: - try: - self.TYPE_DICT_MISC[type(e)](e) - except KeyError: - raise UnknownElementError(type(e)) - if isinstance(e, Group): - self.context = old_context + try: + if isinstance(e, Group): + old_context = self.context + self.context = e.context + if isinstance(e, list): + self.generate_list(e) + elif isinstance(e, ListContainer): + self.generate_ListContainer(e) + elif isinstance(e, Inline): + self.generate_Inline(e) + elif isinstance(e, Block): + self.generate_Block(e) + elif isinstance(e, MetaValue): + self.generate_MetaValue(e) + elif isinstance(e, MetaList): + self.generate_MetaList(e) + else: + try: + method = self.TYPE_DICT_MISC[type(e)] + except KeyError as err: + raise UnknownElementError(type(e)) from err + method(e) + if isinstance(e, Group): + self.context = old_context + except FormatitkoRecursiveError as err: + if not isinstance(e, ListContainer): + err.add_element(e) + raise err + except Exception as err: + raise FormatitkoRecursiveError(e, self.context) from err def escape_special_chars(self, text: str) -> str: return text @@ -247,9 +293,10 @@ class OutputGenerator: def generate_MetaValue(self, e: MetaValue): try: - self.TYPE_DICT_META[type(e)](e) + method = self.TYPE_DICT_META[type(e)] except KeyError: self.generate(e.content) + method(e) def generate_MetaBlocks(self, e: MetaBlocks): self.generate(e.content) @@ -258,16 +305,23 @@ class OutputGenerator: self.generate(e.content) def generate_MetaBool(self, e: MetaBool): - self.generate_simple_tag(e) + if e.boolean: + self.write("True") + else: + self.write("False") def generate_MetaMap(self, e: MetaMap): self.generate_simple_tag(e) def generate_MetaString(self, e: MetaString): - self.generate_simple_tag(e) + self.write(e.text) def generate_Inline(self, e: Inline): - self.TYPE_DICT_INLINE[type(e)](e) + try: + method = self.TYPE_DICT_INLINE[type(e)] + except KeyError as err: + raise UnknownElementError(type(e)) from err + method(e) def generate_Str(self, e: Str): self.write(self.escape_special_chars(e.text)) @@ -368,7 +422,11 @@ class OutputGenerator: def generate_Block(self, e: Block): - self.TYPE_DICT_BLOCK[type(e)](e) + try: + method = self.TYPE_DICT_BLOCK[type(e)] + except KeyError as err: + raise UnknownElementError(type(e)) from err + method(e) # Block elements @@ -433,12 +491,14 @@ class OutputGenerator: self.generate_simple_tag(e) def generate_Doc(self, e: Doc): + if "header-includes" in e.metadata: # This is the pandoc way of doing things + self.generate(e.metadata["header-includes"]) if "header_content" in e.metadata: self.generate(e.metadata["header_content"]) self.generate_simple_tag(e) if "footer_content" in e.metadata: self.generate(e.metadata["footer_content"]) - + def generate_BlockGroup(self, e: BlockGroup): self.generate_simple_tag(e) diff --git a/src/formatitko/tex.py b/src/formatitko/tex.py deleted file mode 100644 index 74b6e6f..0000000 --- a/src/formatitko/tex.py +++ /dev/null @@ -1,270 +0,0 @@ -from panflute import * -import os -from typing import Union - -from .whitespace import NBSP -from .elements import FQuoted -from .util import inlinify -from .context import Group -from .images import ImageProcessor - -# Heavily inspired by: git://git.ucw.cz/labsconf2022.git -def tex(e: Union[Element, ListContainer], i: ImageProcessor, indent_level: int=0, indent_str: str="\t") -> str: - - # `only` attribute which makes transformed elements appear only in tex - # output or html output - if hasattr(e, "attributes") and "only" in e.attributes and e.attributes["only"] != "tex": - return "" - - if isinstance(e, ListContainer): - return ''.join([tex(child, i, indent_level, indent_str) for child in e]) - - # Bits from which the final element output is built at the end of this - # function. Most elements override this by returning their own output. - content_foot = "" - content_head = "" - - arguments = "" - open = "{" - close = "}" - - tag = e.tag.lower() - - tags = { - Header: "h"+chr(64 + e.level) if isinstance(e, Header) else "", - } - if type(e) in tags: - tag = tags[type(e)] - - # These are also disabled in pandoc so they shouldn't appear in the AST at all. - not_implemented = { - Citation: True, - Cite: True, - Definition: True, - DefinitionItem: True, - DefinitionList: True - } - if type(e) in not_implemented: - return f'% FIXME: {type(e)}s not implemented \n' - - # Elements which can be represented by a simple string - simple_string = { - NBSP: "~", - Space: " ", - Null: "", - LineBreak: f"\\\\", - SoftBreak: f" ", - HorizontalRule: "\\hr\n\n" - } - if type(e) in simple_string: - return simple_string[type(e)] - - # Simplest basic elements - if isinstance(e, Str): - return e.text.replace(" ", "~") - - if isinstance(e, Para): - return tex(e.content, i, 0, "")+"\n\n" - - if isinstance(e, Span) or isinstance(e, Plain): - return tex(e.content, i, 0, "") - - # Overriding elements with their own returns - if isinstance(e, Image): - url = e.url - - # TODO: This should use OutputGenerator's get_image_processor_args - # Attributes → image processor args - additional_args = {} - if "file-width" in e.attributes: - additional_args["width"] = int(e.attributes["file-width"]) - if "file-height" in e.attributes: - additional_args["height"] = int(e.attributes["file-height"]) - if "file-quality" in e.attributes: - additional_args["quality"] = int(e.attributes["file-quality"]) - if "file-dpi" in e.attributes: - additional_args["dpi"] = int(e.attributes["file-dpi"]) - - # The directory of the current file, will also look for images there. - source_dir = e.attributes["source_dir"] - - _, ext = os.path.splitext(url) - ext = ext[1:] - - # Conversions between various formats. - if ext in ["pdf", "png", "jpeg"]: - # Even supported elements have to be 'converted' because the - # processing contains finding and moving them to the cache - # directory. - url = i.process_image(url, ext, source_dir, **additional_args) - elif ext in ["svg"]: - url = i.process_image(url, "pdf", source_dir, **additional_args) - elif ext in ["epdf"]: - url = i.process_image(url, "pdf", source_dir, **additional_args) - elif ext in ["jpg"]: - url = i.process_image(url, "jpeg", source_dir, **additional_args) - else: - url = i.process_image(url, "pdf", source_dir, **additional_args) - - url = i.find_image(url, [i.cache_dir]) - width = "" - if "width" in e.attributes: - width = e.attributes["width"] - # 50% → 0.5\hsize - if e.attributes["width"][-1] == "%": - width = str(int(e.attributes["width"][:-1])/100) + "\\hsize" - width = "width " + width - return f'\\image{{{width}}}{{{url}}}' - - if isinstance(e, FQuoted): - if e.style == "cs": - if e.quote_type == "SingleQuote": - return f'‚{tex(e.content, i, 0, "")}‘' - elif e.quote_type == "DoubleQuote": - return f'„{tex(e.content, i, 0, "")}“' - elif e.style == "en": - if e.quote_type == "SingleQuote": - return f'‘{tex(e.content, i, 0, "")}’' - elif e.quote_type == "DoubleQuote": - return f'“{tex(e.content, i, 0, "")}”' - else: - if e.quote_type == "SingleQuote": - return f'\'{tex(e.content, i, 0, "")}\'' - elif e.quote_type == "DoubleQuote": - return f'"{tex(e.content, i, 0, "")}"' - else: - return f'"{tex(e.content, i, 0, "")}"' - - if isinstance(e, Code): - return f'\\verb`{e.text.replace("`", "backtick")}`' - - if isinstance(e, Figure): - return f'\\figure{{{tex(e.content, i, indent_level+1, indent_str)}}}{{{tex(e.caption, i, indent_level+1, indent_str)}}}\n\n' - - # Figure caption - if isinstance(e, Caption): - if inlinify(e) is not None: - return f'\\figcaption{{{tex(e.content, i, 0, "")}}}' - - if isinstance(e, Math): - if e.format == "DisplayMath": - return f'$${e.text}$$\n' - else: - return f'${e.text}$' - - # Footnote - if isinstance(e, Note): - tag = "fn" - if inlinify(e) is not None: - return f'\\fn{{{tex(inlinify(e), i, 0, "")}}}' - - if isinstance(e, Table): - aligns = { - "AlignLeft": "\\quad#\\quad\\hfil", - "AlignRight": "\\quad\\hfil#\\quad", - "AlignCenter": "\\quad\\hfil#\\hfil\\quad", - "AlignDefault": "\\quad#\\quad\\hfil" - } - text = "\strut"+"&".join([aligns[col[0]] for col in e.colspec])+"\cr\n" - text += tex(e.head.content, i, 0, "") - text += "\\noalign{\\hrule}\n" - text += tex(e.content[0].content, i, 0, "") - text += "\\noalign{\\hrule}\n" - text += tex(e.foot.content, i, 0, "") - return "\\vskip1em\n\\halign{"+text+"}\n\\vskip1em\n" - # FIXME: Implement rowspan - - if isinstance(e, TableRow): - return "&".join([("\\multispan"+str(cell.colspan)+" " if cell.colspan > 1 else "")+tex(cell.content, i, 0, "") for cell in e.content])+"\cr\n" - - if isinstance(e, RawInline): - if e.format == "tex": - return e.text - else: - return "" - - if isinstance(e, RawBlock): - if e.format == "tex": - return f'{e.text}\n' - else: - return "" - - # See https://pandoc.org/MANUAL.html#line-blocks - if isinstance(e, LineBlock): - return f'{tex(e.content, i, indent_level+1, indent_str)}\n' - - if isinstance(e, LineItem): - return tex(e.content, i, 0, "") + ("\\\\\n" if e.next else "\n") - - if type(e) is Div: - return f'{tex(e.content, i, indent_level+1, indent_str)}' - - if isinstance(e, Doc): - return tex(e.content, i, indent_level, indent_str)+"\n\\bye" # Is having the \bye a bad idea here? - - - # Non-overriding elements, they get generated using the template at the end - # of this function - if isinstance(e, BulletList): - tag = "list" - open = "" - arguments = "{o}" - close = "\\endlist" - - elif isinstance(e, OrderedList): - tag = "list" - open = "" - styles = { - "DefaultStyle": "n", - "Decimal": "n", - "LowerRoman": "i", - "UpperRoman:": "I", - "LowerAlpha": "a", - "UpperAlpha": "A" - } - style = styles[e.style] - delimiters = { - "DefaultDelim": f"{style}.", - "Period": f"{style}.", - "OneParen": f"{style})", - "TwoParens": f"({style})" - } - style = delimiters[e.delimiter] - arguments = f"{{{style}}}" - close = "\\endlist" - # FIXME: Starting number of list - - elif isinstance(e, ListItem): - tag = ":" - - elif isinstance(e, Link): - if len(e.content) == 1 and isinstance(e.content[0], Str) and e.content[0].text == e.url: - tag = "url" - else: - tag = "linkurl" - arguments = f'{{{e.url}}}' - - elif isinstance(e, Group): - tag = "begingroup" - open = "" - if "lang" in e.metadata and e.metadata["lang"] is not None: - open = "\\language"+e.metadata["lang"] - close = "\\endgroup" - - # The default which all non-overriding elements get generated by. This - # includes elements, which were not explicitly mentioned in this function, - # e. g. Strong, Emph... - - if isinstance(e, Inline): - return f'\\{tag}{arguments}{open}{content_head}{tex(e.content, i, 0, "") if hasattr(e, "_content") else ""}{e.text if hasattr(e, "text") else ""}{content_foot}{close}' - - out_str = "" - out_str = f"\\{tag}{arguments}{open}\n" - out_str += content_head - if hasattr(e, "_content"): - out_str += tex(e.content, i, indent_level+1, indent_str) - if hasattr(e, "text"): - out_str += e.text - out_str += f"{content_foot}\n{close}\n\n" - - return out_str diff --git a/src/formatitko/tex_generator.py b/src/formatitko/tex_generator.py index 476ca2a..5a83d8f 100644 --- a/src/formatitko/tex_generator.py +++ b/src/formatitko/tex_generator.py @@ -8,7 +8,7 @@ from typing import Union import os from .output_generator import OutputGenerator -from .images import ImageProcessor +from .images import ImageProcessor, ImageProcessorNamespaceSearcher from .whitespace import NBSP from .elements import FQuoted @@ -106,9 +106,15 @@ class UCWTexGenerator(OutputGenerator): url = e.url additional_args = self.get_image_processor_args(e.attributes) + additional_args["context"] = self.context - # The directory of the current file, will also look for images there. + # The directory of the current file relative to the current working directory source_dir = self.context.dir + # The directory of the current file relative to the md file we were called on + rel_dir = self.context.rel_dir + + searcher = self.imageProcessor.get_searcher_by_path(url, rel_dir, source_dir) + url = self.imageProcessor.get_path_without_namespace(url) _, ext = os.path.splitext(url) ext = ext[1:] @@ -118,17 +124,17 @@ class UCWTexGenerator(OutputGenerator): # Even supported elements have to be 'converted' because the # processing contains finding and moving them to the cache # directory. - url = self.imageProcessor.process_image(url, ext, source_dir, **additional_args) + url = self.imageProcessor.process_image(url, ext, searcher, **additional_args) elif ext in ["svg"]: # FIXME - url = self.imageProcessor.process_image(url, "pdf", source_dir, **additional_args) + url = self.imageProcessor.process_image(url, "pdf", searcher, **additional_args) elif ext in ["epdf"]: - url = self.imageProcessor.process_image(url, "pdf", source_dir, **additional_args) + url = self.imageProcessor.process_image(url, "pdf", searcher, **additional_args) elif ext in ["jpg"]: - url = self.imageProcessor.process_image(url, "jpeg", source_dir, **additional_args) + url = self.imageProcessor.process_image(url, "jpeg", searcher, **additional_args) else: - url = self.imageProcessor.process_image(url, "pdf", source_dir, **additional_args) + url = self.imageProcessor.process_image(url, "pdf", searcher, **additional_args) - url = self.imageProcessor.find_image(url, [self.imageProcessor.cache_dir]) + url = searcher.get_cache_searcher().find_image(url) width = "" if "width" in e.attributes: width = e.attributes["width"] diff --git a/src/formatitko/transform.py b/src/formatitko/transform.py deleted file mode 100644 index 69679d9..0000000 --- a/src/formatitko/transform.py +++ /dev/null @@ -1,176 +0,0 @@ -from panflute import Element, Div, Span, Quoted, Image, CodeBlock, Str, MetaInlines, MetaString, MetaBool, RawBlock -import re -import os - -# Import local files -from .whitespace import Whitespace, NBSP, bavlna -from .util import nullify, import_md -from .context import Context, BlockGroup -from .command import Command, BlockCommand, InlineCommand -from .command_util import handle_command_define, parse_command -from .elements import FQuoted - - -import warnings -warnings.warn("The transform function has been deprecated, is left only for reference and will be removed in future commits. TransformProcessor should be used in its place.", DeprecationWarning) - -# This is where tha magic happens. This function transforms a single element, -# to transform the entire tree, panflute's walk should be used. -def transform(e: Element, c: Context) -> Element: - - warnings.warn("The transform function has been deprecated, is left only for reference and will be removed in future commits. TransformProcessor should be used in its place.", DeprecationWarning) - # Determine if this space should be non-breakable. See whitespace.py. - if isinstance(e, Whitespace) and bavlna(e, c): - e = NBSP() - - if hasattr(e, "attributes"): - # `if` attribute. Only show this element if flag is set. - if "if" in e.attributes: - if not c.is_flag_set(e.attributes["if"]): - return nullify(e) - # `ifn` attribute. Only show this element if flag is NOT set - if "ifn" in e.attributes: - if c.is_flag_set(e.attributes["ifn"]): - return nullify(e) - - # There are multiple ways to call a command so we turn it into a - # unified element first and then call it at the end. This handles the - # []{c=commandname} and - # :::{c=commandname} - # ::: - # syntax. - if (isinstance(e, Div) or isinstance(e, Span)) and "c" in e.attributes: - if isinstance(e, Div): - e = BlockCommand(*e.content, identifier=e.identifier, classes=e.classes, attributes=e.attributes) - else: - e = InlineCommand(*e.content, identifier=e.identifier, classes=e.classes, attributes=e.attributes) - - # Isolated subdocuments using Group and a different Context. Can be - # separate files (using attribute `partial`) or be inline using the - # following syntax: - # ```markdown {.group} - # * file content * - # ``` - # Both can contain their own metadata in a FrontMatter (YAML header) - if (isinstance(e, Div) and "partial" in e.attributes)\ - or (isinstance(e, CodeBlock) and "markdown" in e.classes and "group" in e.classes): - if isinstance(e, Div): - if not c.trusted: # If we're in an untrusted context, we shouldn't allow inclusion of files outside the PWD. - full_path = os.path.abspath(c.dir + "/" + e.attributes["partial"]) - pwd = os.path.abspath(".") - if os.path.commonpath([full_path, pwd]) != os.path.commonpath([pwd]): - return nullify(e) - text = open(c.dir + "/" + e.attributes["partial"], "r").read() - path = c.dir + "/" + e.attributes["partial"] - else: - text = e.text - path = c.path - if "type" in e.attributes and e.attributes["type"] in ["tex", "html"]: - e = RawBlock(text, e.attributes["type"]) - else: - includedDoc = import_md(text) - trusted = True - if "untrusted" in e.attributes and (e.attributes["untrusted"] == True or e.attributes["untrusted"] == 'True'): - trusted = False - if not c.trusted: - trusted = False - nContext = Context(includedDoc, path, c, trusted=trusted) - language = includedDoc.get_metadata("lang") - includedDoc = includedDoc.walk(transform, nContext) - e = BlockGroup(*includedDoc.content, context=nContext, metadata={"lang": language}) - - # Transform panflute's Quoted to custom FQuoted, see above. - if isinstance(e, Quoted): - quote_styles = { - "cs": "cs", - "en": "en", - "sk": "cs", - None: None - } - e = FQuoted(*e.content, quote_type=e.quote_type, style=quote_styles[c.get_metadata("lang")]) - - if isinstance(e, Image): - # Pass down the directory of the current source file for finding image - # files. - e.attributes["source_dir"] = c.dir - # Pass down "no-srcset" metadatum as attribute down to images. - if not "no-srcset" in e.attributes: - e.attributes["no-srcset"] = c.get_metadata("no-srcset") if c.get_metadata("no-srcset") is not None else False - - # Pass down metadata 'highlight' and 'highlight_style' as attribute to CodeBlocks - if isinstance(e, CodeBlock): - if not "highlight" in e.attributes: - e.attributes["highlight"] = c.get_metadata("highlight") if c.get_metadata("highlight") is not None else True - if not "style" in e.attributes: - e.attributes["style"] = c.get_metadata("highlight-style") if c.get_metadata("highlight-style") is not None else "default" - e.attributes["noclasses"] = False - # I think this is supposed to enable inline styles for highlighting when the style differs from the document, but it clearly doesn't work. a) HTML_generator never accesses it and b) Only the top-level document contains a style so you have to ask the top level context, not the current context. - else: - e.attributes["noclasses"] = True - - # Execute python code inside source code block. Works the same as commands. - # Syntax: - # ```python {.run} - # print("woo") - # ``` - if isinstance(e, CodeBlock) and hasattr(e, "classes") and "python" in e.classes and "run" in e.classes: - if not c.trusted: - return nullify(e) - command_output = parse_command(e.text)(BlockCommand(), c) - e = BlockCommand().replaceSelf(*([] if command_output is None else command_output)) - e = e.walk(transform, c) - - # Command defines for calling using BlockCommand and InlineCommand. If - # redefine is used instead of define, the program doesn't check if the - # command already exists. - # Syntax: - # ```python {define=commandname} - # print(wooo) - # ``` - if isinstance(e, CodeBlock) and hasattr(e, "classes") and "python" in e.classes and hasattr(e, "attributes")\ - and ("define" in e.attributes or "redefine" in e.attributes): - if not c.trusted: - return nullify(e) - e = handle_command_define(e, c) - - ## Shorthands - # Shorter (and sometimes the only) forms of certain features - if isinstance(e, Span) and len(e.content) == 1 and isinstance(e.content[0], Str): - ## Handle special command shorthand [!commandname]{} - if re.match(r"^![\w.]+$", e.content[0].text): - e = InlineCommand(identifier=e.identifier, classes=e.classes, attributes={**e.attributes, "c": e.content[0].text[1:]}) - - ## Handle import [#path/file.md]{} - # This is the exact opposite of partials. We take the commands, flags - # and metadata but drop the content. - elif re.match(r"^#.+$", e.content[0].text): - importedDoc = import_md(open(c.dir + "/" + e.content[0].text[1:], "r").read()) - importedDoc.walk(transform, c) - return nullify(e) - - ## Handle metadata print [$key1.key2]{} - # This is a shorthand for just printing the content of some metadata. - elif re.match(r"^\$[\w.]+$", e.content[0].text): - val = c.get_metadata(e.content[0].text[1:], False) - if isinstance(val, MetaInlines): - e = Span(*val.content) - e = e.walk(transform, c) - elif isinstance(val, MetaString): - e = Span(Str(val.string)) - elif isinstance(val, MetaBool): - e = Span(Str(str(val.boolean))) - else: - raise TypeError(f"Cannot print value of metadatum '{e.content[0].text[1:]}' of type '{type(val)}'") - - ## Execute commands - # panflute's walk function transforms the children first, then the root - # element, so the content the command receives is already transformed. - # The output from the command is then transformed manually again. - if isinstance(e, Command): - if not c.get_command(e.attributes["c"]): - raise NameError(f"Command not defined '{e.attributes['c']}'.") - command_output = c.get_command(e.attributes["c"])(e, c) - e = e.replaceSelf(*command_output) - e = e.walk(transform, c) - - return e diff --git a/src/formatitko/transform_processor.py b/src/formatitko/transform_processor.py index 9e64e1b..9ed995f 100644 --- a/src/formatitko/transform_processor.py +++ b/src/formatitko/transform_processor.py @@ -3,6 +3,7 @@ from panflute import Cite, Code, Emph, Image, LineBreak, Link, Math, Note, Quote from panflute import BlockQuote, BulletList, Citation, CodeBlock, Definition, DefinitionItem, DefinitionList, Div, Figure, Header, HorizontalRule, LineBlock, LineItem, ListItem, MetaBlocks, MetaBool, MetaInlines, MetaList, MetaMap, MetaString, Null, OrderedList, Para, Plain, RawBlock, Table, TableBody, TableFoot, TableHead from panflute import TableRow, TableCell, Caption, Doc from panflute import MetaValue +from panflute.containers import attach from typing import Union, Callable from types import ModuleType @@ -18,17 +19,12 @@ from .context import Group, InlineGroup, BlockGroup from .util import nullify, import_md from .context import Context, CommandCallable from .whitespace import Whitespace, bavlna -from .command import BlockCommand, InlineCommand, CodeCommand, Command +from .command import BlockCommand, InlineCommand, CodeCommand, Command, InlineError from .command_util import handle_command_define, parse_command -from .nop_processor import NOPProcessor, ELCl - -class DoubleDocError(Exception): - "TransformProcessor should only ever see a single Doc." - pass +from .nop_processor import NOPProcessor, ELCl, DoubleDocError class TransformProcessor(NOPProcessor): - context: Union[Context, None] = None root_file_path: str root_highlight_style: str = "default" _command_modules: list[tuple[Union[dict[str, CommandCallable], ModuleType], str]] = [] @@ -44,6 +40,15 @@ class TransformProcessor(NOPProcessor): def add_command_module(self, module: Union[dict[str, CommandCallable], ModuleType], module_name: str=""): self._command_modules.append((module, module_name)) + def init_context(self, e: Doc) -> Context: + if self.context is not None: + raise DoubleDocError() + self.context = Context(e, self.root_file_path) + for module, module_name in self._command_modules: + self.context.add_commands_from_module(module, module_name) + e.content = [BlockGroup(*e.content, context=self.context)] + return self.context + def get_pretransformers(self) -> list[Callable[[ELCl],ELCl]]: return super().get_pretransformers()+[self.handle_if_attribute, self.handle_ifnot_attribute] @@ -61,15 +66,22 @@ class TransformProcessor(NOPProcessor): return nullify(e) return e + def transform_ListContainer(self, e: ListContainer) -> ListContainer: + try: + return super().transform_ListContainer(e) + except TypeError as err: + names = [] + for el in e: + if hasattr(el, "attributes") and "c" in el.attributes: + names.append(el.attributes["c"]) + if len(names) > 0: + raise InlineError(f"The command{'s' if len(names) > 1 else ''} {names[0] if len(names) == 1 else names} was called in an Inline way but returned Block content. Put it in a paragraph alone or execute it as a Div using: \n::: {{c={names[0] if len(names) == 1 else ''}}}\n:::") + else: + raise err def transform_Doc(self, e: Doc) -> Doc: - if self.context is not None: - raise DoubleDocError() - self.context = Context(e, self.root_file_path) - for module, module_name in self._command_modules: - self.context.add_commands_from_module(module, module_name) + self.init_context(e) e.content = self.transform(e.content) - e.content = [BlockGroup(*e.content, context=self.context)] return e @@ -87,19 +99,36 @@ class TransformProcessor(NOPProcessor): e.content = self.transform(e.content) # OG now has Context so this is not needed per se, but I'm keeping this here for the handling of attribute > context > default value # Pass down "no-srcset" metadatum as attribute down to images. - if not "no-srcset" in e.attributes: + if "no-srcset" not in e.attributes: e.attributes["no-srcset"] = self.context.get_metadata("no-srcset") if self.context.get_metadata("no-srcset") is not None else False + if "no-img-link" not in e.attributes: + e.attributes["no-img-link"] = self.context.get_metadata("no-img-link") if self.context.get_metadata("no-img-link") is not None else False return e - def create_Group(self, *content, new_context: Context, inline: bool=False) -> Group: + def create_Group(self, *content, new_context: Context, replaced:Element, inline: bool=False) -> Group: old_context = self.context self.context = new_context - content = self.transform([*content]) - self.context = old_context if inline: - return InlineGroup(*content, context=new_context) + g = InlineGroup(*content, context=new_context) else: - return BlockGroup(*content, context=new_context) + g = BlockGroup(*content, context=new_context) + attach(g, replaced.parent, replaced.location, replaced.index) + g = self.transform(g) + self.context = old_context + return g + + def transform_Para(self, e: Para) -> Union[Para, Div]: + if len(e.content) == 1 and isinstance(e.content[0], Span): + # If the span turns out to be a command, it might return a Div. We should then replace ourselves with the Div + span = e.content[0] + span = self.transform(span) + if isinstance(span, Div): + return span + else: + e.content[0] = span + return super().transform_Para(e) + else: + return super().transform_Para(e) def transform_Div(self, e: Div) -> Union[Div, Group, Null, RawBlock]: e.content = self.transform(e.content) @@ -110,14 +139,15 @@ class TransformProcessor(NOPProcessor): new_context = Context(Doc(), self.context.path, self.context, trusted=self.context.trusted) for attribute, value in e.attributes.items(): new_context.set_metadata(attribute, value) - return self.create_Group(*e.content, new_context=new_context) + return self.create_Group(*e.content, replaced=e, new_context=new_context) if "c" in e.attributes: # Commands can be called multiple ways, this handles the following syntax: # :::{c=commandname} # ::: - e = BlockCommand(*e.content, identifier=e.identifier, classes=e.classes, attributes=e.attributes) - return self.transform(e) + command = BlockCommand(*e.content, identifier=e.identifier, classes=e.classes, attributes=e.attributes) + attach(command, e.parent, e.location, e.index) + return self.transform(command) if "partial" in e.attributes: # `partial` attribute @@ -129,7 +159,9 @@ class TransformProcessor(NOPProcessor): pwd = os.path.abspath(".") if os.path.commonpath([full_path, pwd]) != os.path.commonpath([pwd]): return nullify(e) - text = open(self.context.dir + "/" + e.attributes["partial"], "r").read() + filename = self.context.dir + "/" + e.attributes["partial"] + self.context.add_dep(filename) + text = open(filename, "r").read() path = self.context.dir + "/" + e.attributes["partial"] if e.attributes["type"] == "md": includedDoc = import_md(text) @@ -138,7 +170,7 @@ class TransformProcessor(NOPProcessor): trusted = False if not self.context.trusted: trusted = False - return self.create_Group(*includedDoc.content, new_context=Context(includedDoc, path, self.context, trusted=trusted)) + return self.create_Group(*includedDoc.content, replaced=e, new_context=Context(includedDoc, path, self.context, trusted=trusted)) elif e.attributes["type"] in ["tex", "html"]: return RawBlock(text, e.attributes["type"]) @@ -170,19 +202,21 @@ class TransformProcessor(NOPProcessor): new_context = Context(Doc(), self.context.path, self.context, trusted=self.context.trusted) for attribute, value in e.attributes.items(): new_context.set_metadata(attribute, value) - return self.create_Group(*e.content, new_context=new_context, inline=True) + return self.create_Group(*e.content, replaced=e, new_context=new_context, inline=True) if "c" in e.attributes: # Commands can be called multiple ways, this handles the following syntax: # []{c=commandname} and - e = InlineCommand(*e.content, identifier=e.identifier, classes=e.classes, attributes=e.attributes) - return self.transform(e) + command = InlineCommand(*e.content, identifier=e.identifier, classes=e.classes, attributes=e.attributes) + attach(command, e.parent, e.location, e.index) + return self.transform(command) if len(e.content) == 1 and isinstance(e.content[0], Str): ## Handle special command shorthand [!commandname]{} if re.match(r"^![\w.]+$", e.content[0].text): - e = InlineCommand(identifier=e.identifier, classes=e.classes, attributes={**e.attributes, "c": e.content[0].text[1:]}) - return self.transform(e) + command = InlineCommand(identifier=e.identifier, classes=e.classes, attributes={**e.attributes, "c": e.content[0].text[1:]}) + attach(command, e.parent, e.location, e.index) + return self.transform(command) ## Handle import [#ksp_formatitko as ksp]{}, [#ksp_formatitko]{type=module} or [#path/file.md]{type=md} # Import a python module as commands (type=module, the default) or @@ -191,7 +225,9 @@ class TransformProcessor(NOPProcessor): if not "type" in e.attributes: e.attributes["type"] = "module" if e.attributes["type"] == "md": - importedDoc = import_md(open(self.context.dir + "/" + e.content[0].text[1:], "r").read()) + filename = self.context.dir + "/" + e.content[0].text[1:] + self.context.add_dep(filename) + importedDoc = import_md(open(filename, "r").read()) self.transform(importedDoc.content) elif e.attributes["type"] == "module": matches = re.match(r"^(\w+)(?: as (\w+))?$", e.content[0].text[1:]) @@ -201,7 +237,9 @@ class TransformProcessor(NOPProcessor): module_name = matches.group(1) if matches.group(2) is None else matches.group(2) self.context.add_commands_from_module(module, module_name) elif e.attributes["type"] == "metadata": - data = json.load(open(self.context.dir + "/" + e.content[0].text[1:], "r")) + filename = self.context.dir + "/" + e.content[0].text[1:] + self.context.add_dep(filename) + data = json.load(open(filename, "r")) key = "" if not "key" in e.attributes else e.attributes["key"] self.context.import_metadata(data, key) else: @@ -229,14 +267,15 @@ class TransformProcessor(NOPProcessor): def transform_CodeBlock(self, e: CodeBlock) -> Union[CodeBlock, Div, Null]: if "markdown" in e.classes and "group" in e.classes: includedDoc = import_md(e.text) - return self.create_Group(*includedDoc.content, new_context=Context(includedDoc, self.context.path, self.context, self.context.trusted)) + return self.create_Group(*includedDoc.content, replaced=e, new_context=Context(includedDoc, self.context.path, self.context, self.context.trusted)) if "python" in e.classes and "run" in e.classes: if not self.context.trusted: return nullify(e) - command_output = parse_command(e.text)(BlockCommand(), self.context) - e = BlockCommand().replaceSelf(*([] if command_output is None else command_output)) - return self.transform(e) + command_output = parse_command(e.text)(BlockCommand(), self.context, self) + command = BlockCommand().replaceSelf(*([] if command_output is None else command_output)) + attach(command, e.parent, e.location, e.index) + return self.transform(command) if "python" in e.classes and ("define" in e.attributes or "redefine" in e.attributes): if not self.context.trusted: @@ -244,7 +283,9 @@ class TransformProcessor(NOPProcessor): return handle_command_define(e, self.context) if "c" in e.attributes: - return self.transform(CodeCommand(e.text, identifier=e.identifier, classes=e.classes, attributes=e.attributes)) + command = CodeCommand(e.text, identifier=e.identifier, classes=e.classes, attributes=e.attributes) + attach(command, e.parent, e.location, e.index) + return self.transform(command) # Pass down metadata 'highlight' and 'highlight_style' as attribute to CodeBlocks # OG now has Context so this is not needed per se, but I'm keeping this here for the handling of attribute > context > default value @@ -257,9 +298,9 @@ class TransformProcessor(NOPProcessor): def transform_Command(self, e: Command) -> Union[Div, Span]: if not self.context.get_command(e.attributes["c"]): raise NameError(f"Command not defined '{e.attributes['c']}'.") - command_output = self.context.get_command(e.attributes["c"])(e, self.context) + command_output = self.context.get_command(e.attributes["c"])(e, self.context, self) e = e.replaceSelf(*([] if command_output is None else command_output)) - return self.transform(e) + return e def transform_Whitespace(self, e: Whitespace) -> Whitespace: if bavlna(e, self.context): diff --git a/src/formatitko/util.py b/src/formatitko/util.py index f4eb6b4..0cf614b 100644 --- a/src/formatitko/util.py +++ b/src/formatitko/util.py @@ -37,7 +37,7 @@ def parse_string(s: str) -> list[Union[Str, Space]]: # we ever want to disable or enable some of panflute's markdown extensions, # this is the place to do it. def import_md(s: str, standalone: bool=True) -> Union[Doc, list[Element]]: - return convert_text(s, standalone=standalone, input_format="markdown-definition_lists-latex_macros") + return convert_text(s, standalone=standalone, input_format="markdown-definition_lists-latex_macros", extra_args=["--strip-comments"]) def import_md_list(s: str) -> list[Element]: return import_md(s, standalone=False) diff --git a/test/test-files/test-partial.md b/test/test-files/test-partial.md index 397564b..93455ee 100644 --- a/test/test-files/test-partial.md +++ b/test/test-files/test-partial.md @@ -56,7 +56,15 @@ $$ $$ -```comment + + + + ![This is a figure, go figure...](logo.svg){width=25%}What ![This is a figure, go figure...](logo.pdf){width=50%} ![Fakt epesní reproduktor](reproduktor.jpeg){width=10em} diff --git a/test/test-top.html b/test/test-top.html deleted file mode 100644 index 0cea640..0000000 --- a/test/test-top.html +++ /dev/null @@ -1,8 +0,0 @@ - - - - - - - - diff --git a/test/test.md b/test/test.md index 87929b8..563687c 100644 --- a/test/test.md +++ b/test/test.md @@ -3,12 +3,13 @@ title: 'Wooooo a title' subtitle: 'A subtitle' are_we_there_yet: False lang: "en" +header-includes: | + --- -:::: {.header_content} -::: {partial="test-top.html" type="html"} -::: -:::: - [#test-files/test-import.md]{type=md} [#test.json]{type=metadata key=orgs} @@ -198,12 +199,23 @@ ii. wym bro ```python {define=bash} import subprocess c = subprocess.run(["bash", "-c", element.text], stdout=subprocess.PIPE, check=True, encoding="utf-8") -return [pf.Para(pf.Str(c.stdout))] +return [pf.CodeBlock(c.stdout)] ``` ```bash {c=bash} -cat /etc/hostname +cat /etc/os-release +``` + +::: {.group lang=cs} +```python {.run} +return processor.transform([ + *parse_string("V "), + pf.Link(pf.Str("odevzdávátku"), url="https://ksp.mff.cuni.cz/z/odevzdavatko/"), + *parse_string(" si necháte vygenerovat vstupy a odevzdáte příslušné výstupy. Záleží jen na vás, jak výstupy vyrobíte.") + +]) ``` +::: ```html