tame/tamer/src/xir/flat.rs

652 lines
20 KiB
Rust
Raw Normal View History

// XIR flat (XIRF)
//
// Copyright (C) 2014-2022 Ryan Specialty Group, LLC.
//
// This file is part of TAME.
//
// This program is free software: you can redistribute it and/or modify
// it under the terms of the GNU General Public License as published by
// the Free Software Foundation, either version 3 of the License, or
// (at your option) any later version.
//
// This program is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
// GNU General Public License for more details.
//
// You should have received a copy of the GNU General Public License
// along with this program. If not, see <http://www.gnu.org/licenses/>.
//! Lightly-parsed XIR as a flat stream (XIRF).
//!
//! XIRF lightly parses a raw XIR [`TokenStream`] into a stream of
//! [`XirfToken`]s that are,
//! like a [`TokenStream`],
//! flat in structure.
//! It provides the following features over raw XIR:
//!
//! 1. All closing tags must correspond to a matching opening tag at the
//! same depth;
//! 2. [`XirfToken`] exposes the [`Depth`] of each node-related token;
//! 3. Attribute tokens are parsed into [`Attr`] objects;
//! 4. Documents must begin with an element and end with the closing of
//! that element;
//! 5. Parsing will fail if input ends before all elements have been
//! closed.
tamer: Xirf::Text refinement This teaches XIRF to optionally refine Text into RefinedText, which determines whether the given SymbolId represents entirely whitespace. This is something I've been putting off for some time, but now that I'm parsing source language for NIR, it is necessary, in that we can only permit whitespace Text nodes in certain contexts. The idea is to capture the most common whitespace as preinterned symbols. Note that this heuristic ought to be determined from scanning a codebase, which I haven't done yet; this is just an initial list. The fallback is to look up the string associated with the SymbolId and perform a linear scan, aborting on the first non-whitespace character. This combination of checks should be sufficiently performant for now considering that this is only being run on source files, which really are not all that large. (They become large when template-expanded.) I'll optimize further if I notice it show up during profiling. This also frees XIR itself from being concerned by Whitespace. Initially I had used quick-xml's whitespace trimming, but it messed up my span calculations, and those were a pain in the ass to implement to begin with, since I had to resort to pointer arithmetic. I'd rather avoid tweaking it. tameld will not check for whitespace, since it's not important---xmlo files, if malformed, are the fault of the compiler; we can ignore text nodes except in the context of code fragments, where they are never whitespace (unless that's also a compiler bug). Onward and yonward. DEV-7145
2022-07-27 15:49:38 -04:00
//! 6. Text nodes may optionally be parsed into [`RefinedText`] to
//! distinguish whitespace.
//!
//! XIRF lowering does not perform any dynamic memory allocation;
//! maximum element nesting depth is set statically depending on the needs
//! of the caller.
use super::{
attr::{Attr, AttrParseError, AttrParseState},
tamer: Xirf::Text refinement This teaches XIRF to optionally refine Text into RefinedText, which determines whether the given SymbolId represents entirely whitespace. This is something I've been putting off for some time, but now that I'm parsing source language for NIR, it is necessary, in that we can only permit whitespace Text nodes in certain contexts. The idea is to capture the most common whitespace as preinterned symbols. Note that this heuristic ought to be determined from scanning a codebase, which I haven't done yet; this is just an initial list. The fallback is to look up the string associated with the SymbolId and perform a linear scan, aborting on the first non-whitespace character. This combination of checks should be sufficiently performant for now considering that this is only being run on source files, which really are not all that large. (They become large when template-expanded.) I'll optimize further if I notice it show up during profiling. This also frees XIR itself from being concerned by Whitespace. Initially I had used quick-xml's whitespace trimming, but it messed up my span calculations, and those were a pain in the ass to implement to begin with, since I had to resort to pointer arithmetic. I'd rather avoid tweaking it. tameld will not check for whitespace, since it's not important---xmlo files, if malformed, are the fault of the compiler; we can ignore text nodes except in the context of code fragments, where they are never whitespace (unless that's also a compiler bug). Onward and yonward. DEV-7145
2022-07-27 15:49:38 -04:00
reader::is_xml_whitespace_char,
CloseSpan, OpenSpan, QName, Token as XirToken, TokenStream,
};
use crate::{
diagnose::{Annotate, AnnotatedSpan, Diagnostic},
parse::{
tamer: parse::state::ParseState::Super: Superstate concept I'm disappointed that I keep having to implement features that I had hoped to avoid implementing. This introduces a "superstate" feature, which is intended really just to be a sum type that is able to delegate to stitched `ParseState`s. This then allows a `ParseState` to transition directly to another `ParseState` and have the parent `ParseState` handle the delegation---a trampoline. This issue naturally arises out of the recursive nature of parsing a TAME XML document, where certain statements can be nested (like `<section>`), and where expressions can be nested. I had gotten away with composition-based delegation for now because `xmlo` headers do not have such nesting. The composition-based approach falls flat for recursive structures. The typical naive solution is boxing, which I cannot do, because not only is this on an extremely hot code path, but I require that Rust be able to deeply introspect and optimize away the lowering pipeline as much as possible. Many months ago, I figured that such a solution would require a trampoline, as it typically does in stack-based languages, but I was hoping to avoid it. Well, no longer; let's just get on with it. This intends to implement trampolining in a `ParseState` that serves as that sum type, rather than introducing it as yet another feature to `Parser`; the latter would provide a more convenient API, but it would continue to bloat `Parser` itself. Right now, only the element parser generator will require use of this, so if it's needed beyond that, then I'll debate whether it's worth providing a better abstraction. For now, the intent will be to use the `Context` to store a stack that it can pop off of to restore the previous `ParseState` before delegation. DEV-7145
2022-08-03 12:53:50 -04:00
ClosedParseState, Context, Object, ParseState, ParsedResult, Token,
Transition, TransitionResult,
},
span::Span,
tamer: Xirf::Text refinement This teaches XIRF to optionally refine Text into RefinedText, which determines whether the given SymbolId represents entirely whitespace. This is something I've been putting off for some time, but now that I'm parsing source language for NIR, it is necessary, in that we can only permit whitespace Text nodes in certain contexts. The idea is to capture the most common whitespace as preinterned symbols. Note that this heuristic ought to be determined from scanning a codebase, which I haven't done yet; this is just an initial list. The fallback is to look up the string associated with the SymbolId and perform a linear scan, aborting on the first non-whitespace character. This combination of checks should be sufficiently performant for now considering that this is only being run on source files, which really are not all that large. (They become large when template-expanded.) I'll optimize further if I notice it show up during profiling. This also frees XIR itself from being concerned by Whitespace. Initially I had used quick-xml's whitespace trimming, but it messed up my span calculations, and those were a pain in the ass to implement to begin with, since I had to resort to pointer arithmetic. I'd rather avoid tweaking it. tameld will not check for whitespace, since it's not important---xmlo files, if malformed, are the fault of the compiler; we can ignore text nodes except in the context of code fragments, where they are never whitespace (unless that's also a compiler bug). Onward and yonward. DEV-7145
2022-07-27 15:49:38 -04:00
sym::{st::is_common_whitespace, GlobalSymbolResolve, SymbolId},
tamer: xir: Introduce {Ele,Open,Close}Span This isn't conceptally all that significant of a change, but there was a lot of modify to get it working. I would generally separate this into a commit for the implementation and another commit for the integration, but I decided to keep things together. This serves a role similar to AttrSpan---this allows deriving a span representing the element name from a span representing the entire XIR token. This will provide more useful context for errors---including the tag delimiter(s) means that we care about the fact that an element is in that position (as opposed to some other type of node) within the context of an error. However, if we are expecting an element but take issue with the element name itself, we want to place emphasis on that instead. This also starts to consider the issue of span contexts---a blob of detached data that is `Span` is useful for error context, but it's not useful for manipulation or deriving additional information. For that, we need to encode additional context, and this is an attempt at that. I am interested in the concept of providing Spans that are guaranteed to actually make sense---that are instantiated and manipulated with APIs that ensure consistency. But such a thing buys us very little, practically speaking, over what I have now for TAMER, and so I don't expect to actually implement that for this project; I'll leave that for a personal project. TAMER's already take a lot of my personal interests and it can cause me a lot of grief sometimes (with regards to letting my aspirations cause me more work). DEV-7145
2022-06-24 13:51:49 -04:00
xir::EleSpan,
};
use arrayvec::ArrayVec;
tamer: Xirf::Text refinement This teaches XIRF to optionally refine Text into RefinedText, which determines whether the given SymbolId represents entirely whitespace. This is something I've been putting off for some time, but now that I'm parsing source language for NIR, it is necessary, in that we can only permit whitespace Text nodes in certain contexts. The idea is to capture the most common whitespace as preinterned symbols. Note that this heuristic ought to be determined from scanning a codebase, which I haven't done yet; this is just an initial list. The fallback is to look up the string associated with the SymbolId and perform a linear scan, aborting on the first non-whitespace character. This combination of checks should be sufficiently performant for now considering that this is only being run on source files, which really are not all that large. (They become large when template-expanded.) I'll optimize further if I notice it show up during profiling. This also frees XIR itself from being concerned by Whitespace. Initially I had used quick-xml's whitespace trimming, but it messed up my span calculations, and those were a pain in the ass to implement to begin with, since I had to resort to pointer arithmetic. I'd rather avoid tweaking it. tameld will not check for whitespace, since it's not important---xmlo files, if malformed, are the fault of the compiler; we can ignore text nodes except in the context of code fragments, where they are never whitespace (unless that's also a compiler bug). Onward and yonward. DEV-7145
2022-07-27 15:49:38 -04:00
use std::{
error::Error,
fmt::{Debug, Display},
marker::PhantomData,
};
/// Tag nesting depth
/// (`0` represents the root).
tamer: xir::parse::ele: Introduce sum nonterminals This introduces `Nt := (A | ... | Z);`, where `Nt` is the name of the nonterminal and `A ... Z` are the inner nonterminals---it produces a parser that provides a choice between a set of nonterminals. This is implemented efficiently by understanding the QName that is accepted by each of the inner nonterminals and delegating that token immediately to the appropriate parser. This is a benefit of using a parser generator macro over parser combinators---we do not need to implement backtracking by letting inner parsers fail, because we know ahead of time exactly what parser we need. This _does not_ verify that each of the inner parsers accept a unique QName; maybe at a later time I can figure out something for that. However, because this compiles into a `match`, there is no ambiguity---like a PEG parser, there is precedence in the face of an ambiguous token, and the first one wins. Consequently, tests would surely fail, since the latter wouldn't be able to be parsed. This also demonstrates how we can have good error suggestions for this parsing framework: because the inner nonterminals and their QNames are known at compile time, error messages simply generate a list of QNames that are expected. The error recovery strategy is the same as previously noted, and subject to the same concerns, though it may be more appropriate here: it is desirable for the inner parser to fail rather than retrying, so that the sum parser is able to fail and, once the Kleene operator is introduced, retry on another potential element. But again, that recovery strategy may happen to work in some cases, but'll fail miserably in others (e.g. placing an unknown element at the head of a block that expects a sequence of elements would potentially fail the entire block rather than just the invalid one). But more to come on that later; it's not critical at this point. I need to get parsing completed for TAME's input language. DEV-7145
2022-07-14 15:12:57 -04:00
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
tamer: obj::xmlo::reader: Begin conversion to ParseState This begins to transition XmloReader into a ParseState. Unlike previous changes where ParseStates were composed into a single ParseState, this is instead a lowering operation that will take the output of one Parser and provide it to another. The mess in ld::poc (...which still needs to be refactored and removed) shows the concept, which will be abstracted away. This won't actually get to the ASG in order to test that that this works with the wip-xmlo-xir-reader flag on (development hasn't gotten that far yet), but since it type-checks, it should conceptually work. Wiring lowering operations together is something that I've been dreading for months, but my approach of only abstracting after-the-fact has helped to guide a sane approach for this. For some definition of "sane". It's also worth noting that AsgBuilder will too become a ParseState implemented as another lowering operation, so: XIR -> XIRF -> XMLO -> ASG These steps will all be streaming, with iteration happening only at the topmost level. For this reason, it's important that ASG not be responsible for doing that pull, and further we should propagate Parsed::Incomplete rather than filtering it out and looping an indeterminate number of times outside of the toplevel. One final note: the choice of 64 for the maximum depth is entirely arbitrary and should be more than generous; it'll be finalized at some point in the future once I actually evaluate what maximum depth is reasonable based on how the system is used, with some added growing room. DEV-10863
2022-03-22 13:56:43 -04:00
pub struct Depth(pub usize);
impl Depth {
/// Yield a new [`Depth`] representing the expected depth of children of
/// an element at the current depth.
///
/// That description is probably more confusing than the method name.
pub fn child_depth(&self) -> Depth {
match self {
Depth(depth) => Depth(depth + 1),
}
}
}
impl Display for Depth {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
Display::fmt(&self.0, f)
}
}
/// A lightly-parsed XIRF object.
///
/// Certain XIR [`Token`]s are formed into a single object,
/// such as an [`Attr`].
/// Other objects retain the same format as their underlying token,
/// but are still validated to ensure that they are well-formed and that
/// the XML is well-structured.
///
/// Each token representing a child node contains a numeric [`Depth`]
/// indicating the nesting depth;
/// this can be used by downstream parsers to avoid maintaining their
/// own stack in certain cases.
#[derive(Debug, Clone, PartialEq, Eq)]
tamer: Xirf::Text refinement This teaches XIRF to optionally refine Text into RefinedText, which determines whether the given SymbolId represents entirely whitespace. This is something I've been putting off for some time, but now that I'm parsing source language for NIR, it is necessary, in that we can only permit whitespace Text nodes in certain contexts. The idea is to capture the most common whitespace as preinterned symbols. Note that this heuristic ought to be determined from scanning a codebase, which I haven't done yet; this is just an initial list. The fallback is to look up the string associated with the SymbolId and perform a linear scan, aborting on the first non-whitespace character. This combination of checks should be sufficiently performant for now considering that this is only being run on source files, which really are not all that large. (They become large when template-expanded.) I'll optimize further if I notice it show up during profiling. This also frees XIR itself from being concerned by Whitespace. Initially I had used quick-xml's whitespace trimming, but it messed up my span calculations, and those were a pain in the ass to implement to begin with, since I had to resort to pointer arithmetic. I'd rather avoid tweaking it. tameld will not check for whitespace, since it's not important---xmlo files, if malformed, are the fault of the compiler; we can ignore text nodes except in the context of code fragments, where they are never whitespace (unless that's also a compiler bug). Onward and yonward. DEV-7145
2022-07-27 15:49:38 -04:00
pub enum XirfToken<T: TextType> {
/// Opening tag of an element.
tamer: xir: Introduce {Ele,Open,Close}Span This isn't conceptally all that significant of a change, but there was a lot of modify to get it working. I would generally separate this into a commit for the implementation and another commit for the integration, but I decided to keep things together. This serves a role similar to AttrSpan---this allows deriving a span representing the element name from a span representing the entire XIR token. This will provide more useful context for errors---including the tag delimiter(s) means that we care about the fact that an element is in that position (as opposed to some other type of node) within the context of an error. However, if we are expecting an element but take issue with the element name itself, we want to place emphasis on that instead. This also starts to consider the issue of span contexts---a blob of detached data that is `Span` is useful for error context, but it's not useful for manipulation or deriving additional information. For that, we need to encode additional context, and this is an attempt at that. I am interested in the concept of providing Spans that are guaranteed to actually make sense---that are instantiated and manipulated with APIs that ensure consistency. But such a thing buys us very little, practically speaking, over what I have now for TAMER, and so I don't expect to actually implement that for this project; I'll leave that for a personal project. TAMER's already take a lot of my personal interests and it can cause me a lot of grief sometimes (with regards to letting my aspirations cause me more work). DEV-7145
2022-06-24 13:51:49 -04:00
Open(QName, OpenSpan, Depth),
/// Closing tag of an element.
///
/// If the name is [`None`],
/// then the tag is self-closing.
/// If the name is [`Some`],
/// then the tag is guaranteed to be balanced
/// (matching the depth of its opening tag).
tamer: xir: Introduce {Ele,Open,Close}Span This isn't conceptally all that significant of a change, but there was a lot of modify to get it working. I would generally separate this into a commit for the implementation and another commit for the integration, but I decided to keep things together. This serves a role similar to AttrSpan---this allows deriving a span representing the element name from a span representing the entire XIR token. This will provide more useful context for errors---including the tag delimiter(s) means that we care about the fact that an element is in that position (as opposed to some other type of node) within the context of an error. However, if we are expecting an element but take issue with the element name itself, we want to place emphasis on that instead. This also starts to consider the issue of span contexts---a blob of detached data that is `Span` is useful for error context, but it's not useful for manipulation or deriving additional information. For that, we need to encode additional context, and this is an attempt at that. I am interested in the concept of providing Spans that are guaranteed to actually make sense---that are instantiated and manipulated with APIs that ensure consistency. But such a thing buys us very little, practically speaking, over what I have now for TAMER, and so I don't expect to actually implement that for this project; I'll leave that for a personal project. TAMER's already take a lot of my personal interests and it can cause me a lot of grief sometimes (with regards to letting my aspirations cause me more work). DEV-7145
2022-06-24 13:51:49 -04:00
Close(Option<QName>, CloseSpan, Depth),
/// An attribute and its value.
///
/// The associated [`Span`]s can be found on the enclosed [`Attr`]
/// object.
Attr(Attr),
/// Comment node.
Comment(SymbolId, Span, Depth),
/// Character data as part of an element.
///
/// See also [`CData`](XirfToken::CData) variant.
Text(T, Depth),
/// CData node (`<![CDATA[...]]>`).
///
/// _Warning: It is up to the caller to ensure that the string `]]>` is
/// not present in the text!_
/// This is intended for reading existing XML data where CData is
/// already present,
/// not for producing new CData safely!
CData(SymbolId, Span, Depth),
}
tamer: Xirf::Text refinement This teaches XIRF to optionally refine Text into RefinedText, which determines whether the given SymbolId represents entirely whitespace. This is something I've been putting off for some time, but now that I'm parsing source language for NIR, it is necessary, in that we can only permit whitespace Text nodes in certain contexts. The idea is to capture the most common whitespace as preinterned symbols. Note that this heuristic ought to be determined from scanning a codebase, which I haven't done yet; this is just an initial list. The fallback is to look up the string associated with the SymbolId and perform a linear scan, aborting on the first non-whitespace character. This combination of checks should be sufficiently performant for now considering that this is only being run on source files, which really are not all that large. (They become large when template-expanded.) I'll optimize further if I notice it show up during profiling. This also frees XIR itself from being concerned by Whitespace. Initially I had used quick-xml's whitespace trimming, but it messed up my span calculations, and those were a pain in the ass to implement to begin with, since I had to resort to pointer arithmetic. I'd rather avoid tweaking it. tameld will not check for whitespace, since it's not important---xmlo files, if malformed, are the fault of the compiler; we can ignore text nodes except in the context of code fragments, where they are never whitespace (unless that's also a compiler bug). Onward and yonward. DEV-7145
2022-07-27 15:49:38 -04:00
impl<T: TextType> Token for XirfToken<T> {
tamer: parser::Parser: cfg(test) tracing This produces useful parse traces that are output as part of a failing test case. The parser generator macros can be a bit confusing to deal with when things go wrong, so this helps to clarify matters. This is _not_ intended to be machine-readable, but it does show that it would be possible to generate machine-readable output to visualize the entire lowering pipeline. Perhaps something for the future. I left these inline in Parser::feed_tok because they help to elucidate what is going on, just by reading what the trace would output---that is, it helps to make the method more self-documenting, albeit a tad bit more verbose. But with that said, it should probably be extracted at some point; I don't want this to set a precedent where composition is feasible. Here's an example from test cases: [Parser::feed_tok] (input IR: XIRF) | ==> Parser before tok is parsing attributes for `package`. | | Attrs_(SutAttrsState_ { ___ctx: (QName(None, LocalPart(NCName(SymbolId(46 "package")))), OpenSpan(Span { len: 0, offset: 0, ctx: Context(SymbolId(1 "#!DUMMY")) }, 10)), ___done: false }) | | ==> XIRF tok: `<unexpected>` | | Open(QName(None, LocalPart(NCName(SymbolId(82 "unexpected")))), OpenSpan(Span { len: 0, offset: 1, ctx: Context(SymbolId(1 "#!DUMMY")) }, 10), Depth(1)) | | ==> Parser after tok is expecting opening tag `<classify>`. | | ChildA(Expecting_) | | Lookahead: Some(Lookahead(Open(QName(None, LocalPart(NCName(SymbolId(82 "unexpected")))), OpenSpan(Span { len: 0, offset: 1, ctx: Context(SymbolId(1 "#!DUMMY")) }, 10), Depth(1)))) = note: this trace was output as a debugging aid because `cfg(test)`. [Parser::feed_tok] (input IR: XIRF) | ==> Parser before tok is expecting opening tag `<classify>`. | | ChildA(Expecting_) | | ==> XIRF tok: `<unexpected>` | | Open(QName(None, LocalPart(NCName(SymbolId(82 "unexpected")))), OpenSpan(Span { len: 0, offset: 1, ctx: Context(SymbolId(1 "#!DUMMY")) }, 10), Depth(1)) | | ==> Parser after tok is attempting to recover by ignoring element with unexpected name `unexpected` (expected `classify`). | | ChildA(RecoverEleIgnore_(QName(None, LocalPart(NCName(SymbolId(82 "unexpected")))), OpenSpan(Span { len: 0, offset: 1, ctx: Context(SymbolId(1 "#!DUMMY")) }, 10), Depth(1))) | | Lookahead: None = note: this trace was output as a debugging aid because `cfg(test)`. DEV-7145
2022-07-18 14:32:34 -04:00
fn ir_name() -> &'static str {
"XIRF"
}
fn span(&self) -> Span {
use XirfToken::*;
match self {
tamer: xir: Introduce {Ele,Open,Close}Span This isn't conceptally all that significant of a change, but there was a lot of modify to get it working. I would generally separate this into a commit for the implementation and another commit for the integration, but I decided to keep things together. This serves a role similar to AttrSpan---this allows deriving a span representing the element name from a span representing the entire XIR token. This will provide more useful context for errors---including the tag delimiter(s) means that we care about the fact that an element is in that position (as opposed to some other type of node) within the context of an error. However, if we are expecting an element but take issue with the element name itself, we want to place emphasis on that instead. This also starts to consider the issue of span contexts---a blob of detached data that is `Span` is useful for error context, but it's not useful for manipulation or deriving additional information. For that, we need to encode additional context, and this is an attempt at that. I am interested in the concept of providing Spans that are guaranteed to actually make sense---that are instantiated and manipulated with APIs that ensure consistency. But such a thing buys us very little, practically speaking, over what I have now for TAMER, and so I don't expect to actually implement that for this project; I'll leave that for a personal project. TAMER's already take a lot of my personal interests and it can cause me a lot of grief sometimes (with regards to letting my aspirations cause me more work). DEV-7145
2022-06-24 13:51:49 -04:00
Open(_, OpenSpan(span, _), _)
| Close(_, CloseSpan(span, _), _)
| Comment(_, span, _)
| CData(_, span, _) => *span,
Text(text, _) => text.span(),
Attr(attr) => attr.span(),
}
}
}
tamer: Xirf::Text refinement This teaches XIRF to optionally refine Text into RefinedText, which determines whether the given SymbolId represents entirely whitespace. This is something I've been putting off for some time, but now that I'm parsing source language for NIR, it is necessary, in that we can only permit whitespace Text nodes in certain contexts. The idea is to capture the most common whitespace as preinterned symbols. Note that this heuristic ought to be determined from scanning a codebase, which I haven't done yet; this is just an initial list. The fallback is to look up the string associated with the SymbolId and perform a linear scan, aborting on the first non-whitespace character. This combination of checks should be sufficiently performant for now considering that this is only being run on source files, which really are not all that large. (They become large when template-expanded.) I'll optimize further if I notice it show up during profiling. This also frees XIR itself from being concerned by Whitespace. Initially I had used quick-xml's whitespace trimming, but it messed up my span calculations, and those were a pain in the ass to implement to begin with, since I had to resort to pointer arithmetic. I'd rather avoid tweaking it. tameld will not check for whitespace, since it's not important---xmlo files, if malformed, are the fault of the compiler; we can ignore text nodes except in the context of code fragments, where they are never whitespace (unless that's also a compiler bug). Onward and yonward. DEV-7145
2022-07-27 15:49:38 -04:00
impl<T: TextType> Object for XirfToken<T> {}
tamer: Xirf::Text refinement This teaches XIRF to optionally refine Text into RefinedText, which determines whether the given SymbolId represents entirely whitespace. This is something I've been putting off for some time, but now that I'm parsing source language for NIR, it is necessary, in that we can only permit whitespace Text nodes in certain contexts. The idea is to capture the most common whitespace as preinterned symbols. Note that this heuristic ought to be determined from scanning a codebase, which I haven't done yet; this is just an initial list. The fallback is to look up the string associated with the SymbolId and perform a linear scan, aborting on the first non-whitespace character. This combination of checks should be sufficiently performant for now considering that this is only being run on source files, which really are not all that large. (They become large when template-expanded.) I'll optimize further if I notice it show up during profiling. This also frees XIR itself from being concerned by Whitespace. Initially I had used quick-xml's whitespace trimming, but it messed up my span calculations, and those were a pain in the ass to implement to begin with, since I had to resort to pointer arithmetic. I'd rather avoid tweaking it. tameld will not check for whitespace, since it's not important---xmlo files, if malformed, are the fault of the compiler; we can ignore text nodes except in the context of code fragments, where they are never whitespace (unless that's also a compiler bug). Onward and yonward. DEV-7145
2022-07-27 15:49:38 -04:00
impl<T: TextType> Display for XirfToken<T> {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
use XirfToken::*;
match self {
Open(qname, span, _) => {
Display::fmt(&XirToken::Open(*qname, *span), f)
}
Close(oqname, span, _) => {
Display::fmt(&XirToken::Close(*oqname, *span), f)
}
Attr(attr) => Display::fmt(&attr, f),
Comment(sym, span, _) => {
Display::fmt(&XirToken::Comment(*sym, *span), f)
}
Text(text, _) => Display::fmt(text, f),
CData(sym, span, _) => {
Display::fmt(&XirToken::CData(*sym, *span), f)
}
}
}
}
tamer: Xirf::Text refinement This teaches XIRF to optionally refine Text into RefinedText, which determines whether the given SymbolId represents entirely whitespace. This is something I've been putting off for some time, but now that I'm parsing source language for NIR, it is necessary, in that we can only permit whitespace Text nodes in certain contexts. The idea is to capture the most common whitespace as preinterned symbols. Note that this heuristic ought to be determined from scanning a codebase, which I haven't done yet; this is just an initial list. The fallback is to look up the string associated with the SymbolId and perform a linear scan, aborting on the first non-whitespace character. This combination of checks should be sufficiently performant for now considering that this is only being run on source files, which really are not all that large. (They become large when template-expanded.) I'll optimize further if I notice it show up during profiling. This also frees XIR itself from being concerned by Whitespace. Initially I had used quick-xml's whitespace trimming, but it messed up my span calculations, and those were a pain in the ass to implement to begin with, since I had to resort to pointer arithmetic. I'd rather avoid tweaking it. tameld will not check for whitespace, since it's not important---xmlo files, if malformed, are the fault of the compiler; we can ignore text nodes except in the context of code fragments, where they are never whitespace (unless that's also a compiler bug). Onward and yonward. DEV-7145
2022-07-27 15:49:38 -04:00
impl<T: TextType> From<Attr> for XirfToken<T> {
fn from(attr: Attr) -> Self {
Self::Attr(attr)
}
}
tamer: Xirf::Text refinement This teaches XIRF to optionally refine Text into RefinedText, which determines whether the given SymbolId represents entirely whitespace. This is something I've been putting off for some time, but now that I'm parsing source language for NIR, it is necessary, in that we can only permit whitespace Text nodes in certain contexts. The idea is to capture the most common whitespace as preinterned symbols. Note that this heuristic ought to be determined from scanning a codebase, which I haven't done yet; this is just an initial list. The fallback is to look up the string associated with the SymbolId and perform a linear scan, aborting on the first non-whitespace character. This combination of checks should be sufficiently performant for now considering that this is only being run on source files, which really are not all that large. (They become large when template-expanded.) I'll optimize further if I notice it show up during profiling. This also frees XIR itself from being concerned by Whitespace. Initially I had used quick-xml's whitespace trimming, but it messed up my span calculations, and those were a pain in the ass to implement to begin with, since I had to resort to pointer arithmetic. I'd rather avoid tweaking it. tameld will not check for whitespace, since it's not important---xmlo files, if malformed, are the fault of the compiler; we can ignore text nodes except in the context of code fragments, where they are never whitespace (unless that's also a compiler bug). Onward and yonward. DEV-7145
2022-07-27 15:49:38 -04:00
/// Token of an optionally refined [`Text`].
///
/// XIRF is configurable on the type of processing it performs on [`Text`],
/// including the detection of [`Whitespace`].
///
/// See also [`RefinedText`].
pub trait TextType = From<Text> + Token + Eq;
#[derive(Debug, PartialEq, Eq, Clone)]
pub struct Text(pub SymbolId, pub Span);
impl Token for Text {
fn ir_name() -> &'static str {
"XIRF Text"
}
fn span(&self) -> Span {
match self {
Self(_, span) => *span,
}
}
}
impl Display for Text {
fn fmt(&self, f: &mut std::fmt::Formatter) -> std::fmt::Result {
// TODO: We'll need care to output text so that it does not mess up
// formatted output.
// Further,
// text can be any arbitrary length,
// and so should probably be elided after a certain length.
write!(f, "text")
}
}
/// A sequence of one or more whitespace characters.
///
/// Whitespace here is expected to consist of `[ \n\t\r]`
/// (where the first character in that class is a space).
#[derive(Debug, PartialEq, Eq, Clone)]
pub struct Whitespace(pub Text);
impl Display for Whitespace {
fn fmt(&self, f: &mut std::fmt::Formatter) -> std::fmt::Result {
// TODO: Escape output as necessary so that we can render the symbol
// string.
// See also `<Text as Display>::fmt` TODO.
write!(f, "whitespace")
}
}
/// Text that has been refined to a more descriptive form.
///
/// This type may be used as a [`TextType`] to instruct XIRF to detect
/// [`Whitespace`].
#[derive(Debug, PartialEq, Eq, Clone)]
pub enum RefinedText {
/// Provided [`Text`] has been determined to be [`Whitespace`].
Whitespace(Whitespace),
/// Provided [`Text`] was not able to be refined into a more specific
/// type.
Unrefined(Text),
}
impl Token for RefinedText {
fn ir_name() -> &'static str {
"XIRF RefinedText"
}
fn span(&self) -> Span {
match self {
Self::Whitespace(Whitespace(text)) | Self::Unrefined(text) => {
text.span()
}
}
}
}
impl Display for RefinedText {
fn fmt(&self, f: &mut std::fmt::Formatter) -> std::fmt::Result {
match self {
Self::Whitespace(ws) => Display::fmt(ws, f),
Self::Unrefined(text) => Display::fmt(text, f),
}
}
}
impl From<Text> for RefinedText {
fn from(text: Text) -> Self {
match text {
Text(sym, _) if is_whitespace(sym) => {
Self::Whitespace(Whitespace(text))
}
_ => Self::Unrefined(text),
}
}
}
/// XIRF-compatible attribute parser.
pub trait FlatAttrParseState<const MAX_DEPTH: usize> =
tamer: parse::state::ParseState::Super: Superstate concept I'm disappointed that I keep having to implement features that I had hoped to avoid implementing. This introduces a "superstate" feature, which is intended really just to be a sum type that is able to delegate to stitched `ParseState`s. This then allows a `ParseState` to transition directly to another `ParseState` and have the parent `ParseState` handle the delegation---a trampoline. This issue naturally arises out of the recursive nature of parsing a TAME XML document, where certain statements can be nested (like `<section>`), and where expressions can be nested. I had gotten away with composition-based delegation for now because `xmlo` headers do not have such nesting. The composition-based approach falls flat for recursive structures. The typical naive solution is boxing, which I cannot do, because not only is this on an extremely hot code path, but I require that Rust be able to deeply introspect and optimize away the lowering pipeline as much as possible. Many months ago, I figured that such a solution would require a trampoline, as it typically does in stack-based languages, but I was hoping to avoid it. Well, no longer; let's just get on with it. This intends to implement trampolining in a `ParseState` that serves as that sum type, rather than introducing it as yet another feature to `Parser`; the latter would provide a more convenient API, but it would continue to bloat `Parser` itself. Right now, only the element parser generator will require use of this, so if it's needed beyond that, then I'll debate whether it's worth providing a better abstraction. For now, the intent will be to use the `Context` to store a stack that it can pop off of to restore the previous `ParseState` before delegation. DEV-7145
2022-08-03 12:53:50 -04:00
ClosedParseState<Token = XirToken, Object = Attr>
where
Self: Default,
<Self as ParseState>::Error: Into<XirToXirfError>,
StateContext<MAX_DEPTH>: AsMut<<Self as ParseState>::Context>;
/// Stack of element [`QName`] and [`Span`] pairs,
/// representing the current level of nesting.
///
/// This storage is statically allocated,
/// allowing XIRF's parser to avoid memory allocation entirely.
type ElementStack<const MAX_DEPTH: usize> = ArrayVec<(QName, Span), MAX_DEPTH>;
/// XIRF document parser state.
///
/// This parser is a pushdown automaton that parses a single XML document.
tamer: Xirf::Text refinement This teaches XIRF to optionally refine Text into RefinedText, which determines whether the given SymbolId represents entirely whitespace. This is something I've been putting off for some time, but now that I'm parsing source language for NIR, it is necessary, in that we can only permit whitespace Text nodes in certain contexts. The idea is to capture the most common whitespace as preinterned symbols. Note that this heuristic ought to be determined from scanning a codebase, which I haven't done yet; this is just an initial list. The fallback is to look up the string associated with the SymbolId and perform a linear scan, aborting on the first non-whitespace character. This combination of checks should be sufficiently performant for now considering that this is only being run on source files, which really are not all that large. (They become large when template-expanded.) I'll optimize further if I notice it show up during profiling. This also frees XIR itself from being concerned by Whitespace. Initially I had used quick-xml's whitespace trimming, but it messed up my span calculations, and those were a pain in the ass to implement to begin with, since I had to resort to pointer arithmetic. I'd rather avoid tweaking it. tameld will not check for whitespace, since it's not important---xmlo files, if malformed, are the fault of the compiler; we can ignore text nodes except in the context of code fragments, where they are never whitespace (unless that's also a compiler bug). Onward and yonward. DEV-7145
2022-07-27 15:49:38 -04:00
#[derive(Debug, PartialEq, Eq)]
pub enum XirToXirf<const MAX_DEPTH: usize, T, SA = AttrParseState>
where
SA: FlatAttrParseState<MAX_DEPTH>,
tamer: Xirf::Text refinement This teaches XIRF to optionally refine Text into RefinedText, which determines whether the given SymbolId represents entirely whitespace. This is something I've been putting off for some time, but now that I'm parsing source language for NIR, it is necessary, in that we can only permit whitespace Text nodes in certain contexts. The idea is to capture the most common whitespace as preinterned symbols. Note that this heuristic ought to be determined from scanning a codebase, which I haven't done yet; this is just an initial list. The fallback is to look up the string associated with the SymbolId and perform a linear scan, aborting on the first non-whitespace character. This combination of checks should be sufficiently performant for now considering that this is only being run on source files, which really are not all that large. (They become large when template-expanded.) I'll optimize further if I notice it show up during profiling. This also frees XIR itself from being concerned by Whitespace. Initially I had used quick-xml's whitespace trimming, but it messed up my span calculations, and those were a pain in the ass to implement to begin with, since I had to resort to pointer arithmetic. I'd rather avoid tweaking it. tameld will not check for whitespace, since it's not important---xmlo files, if malformed, are the fault of the compiler; we can ignore text nodes except in the context of code fragments, where they are never whitespace (unless that's also a compiler bug). Onward and yonward. DEV-7145
2022-07-27 15:49:38 -04:00
T: TextType,
{
/// Document parsing has not yet begun.
tamer: Xirf::Text refinement This teaches XIRF to optionally refine Text into RefinedText, which determines whether the given SymbolId represents entirely whitespace. This is something I've been putting off for some time, but now that I'm parsing source language for NIR, it is necessary, in that we can only permit whitespace Text nodes in certain contexts. The idea is to capture the most common whitespace as preinterned symbols. Note that this heuristic ought to be determined from scanning a codebase, which I haven't done yet; this is just an initial list. The fallback is to look up the string associated with the SymbolId and perform a linear scan, aborting on the first non-whitespace character. This combination of checks should be sufficiently performant for now considering that this is only being run on source files, which really are not all that large. (They become large when template-expanded.) I'll optimize further if I notice it show up during profiling. This also frees XIR itself from being concerned by Whitespace. Initially I had used quick-xml's whitespace trimming, but it messed up my span calculations, and those were a pain in the ass to implement to begin with, since I had to resort to pointer arithmetic. I'd rather avoid tweaking it. tameld will not check for whitespace, since it's not important---xmlo files, if malformed, are the fault of the compiler; we can ignore text nodes except in the context of code fragments, where they are never whitespace (unless that's also a compiler bug). Onward and yonward. DEV-7145
2022-07-27 15:49:38 -04:00
PreRoot(PhantomData<T>),
/// Parsing nodes.
NodeExpected,
/// Delegating to attribute parser.
AttrExpected(SA),
/// End of document has been reached.
Done,
}
tamer: Xirf::Text refinement This teaches XIRF to optionally refine Text into RefinedText, which determines whether the given SymbolId represents entirely whitespace. This is something I've been putting off for some time, but now that I'm parsing source language for NIR, it is necessary, in that we can only permit whitespace Text nodes in certain contexts. The idea is to capture the most common whitespace as preinterned symbols. Note that this heuristic ought to be determined from scanning a codebase, which I haven't done yet; this is just an initial list. The fallback is to look up the string associated with the SymbolId and perform a linear scan, aborting on the first non-whitespace character. This combination of checks should be sufficiently performant for now considering that this is only being run on source files, which really are not all that large. (They become large when template-expanded.) I'll optimize further if I notice it show up during profiling. This also frees XIR itself from being concerned by Whitespace. Initially I had used quick-xml's whitespace trimming, but it messed up my span calculations, and those were a pain in the ass to implement to begin with, since I had to resort to pointer arithmetic. I'd rather avoid tweaking it. tameld will not check for whitespace, since it's not important---xmlo files, if malformed, are the fault of the compiler; we can ignore text nodes except in the context of code fragments, where they are never whitespace (unless that's also a compiler bug). Onward and yonward. DEV-7145
2022-07-27 15:49:38 -04:00
impl<const MAX_DEPTH: usize, T, SA> Default for XirToXirf<MAX_DEPTH, T, SA>
where
SA: FlatAttrParseState<MAX_DEPTH>,
T: TextType,
{
fn default() -> Self {
Self::PreRoot(PhantomData::default())
}
}
pub type StateContext<const MAX_DEPTH: usize> =
Context<ElementStack<MAX_DEPTH>>;
tamer: Xirf::Text refinement This teaches XIRF to optionally refine Text into RefinedText, which determines whether the given SymbolId represents entirely whitespace. This is something I've been putting off for some time, but now that I'm parsing source language for NIR, it is necessary, in that we can only permit whitespace Text nodes in certain contexts. The idea is to capture the most common whitespace as preinterned symbols. Note that this heuristic ought to be determined from scanning a codebase, which I haven't done yet; this is just an initial list. The fallback is to look up the string associated with the SymbolId and perform a linear scan, aborting on the first non-whitespace character. This combination of checks should be sufficiently performant for now considering that this is only being run on source files, which really are not all that large. (They become large when template-expanded.) I'll optimize further if I notice it show up during profiling. This also frees XIR itself from being concerned by Whitespace. Initially I had used quick-xml's whitespace trimming, but it messed up my span calculations, and those were a pain in the ass to implement to begin with, since I had to resort to pointer arithmetic. I'd rather avoid tweaking it. tameld will not check for whitespace, since it's not important---xmlo files, if malformed, are the fault of the compiler; we can ignore text nodes except in the context of code fragments, where they are never whitespace (unless that's also a compiler bug). Onward and yonward. DEV-7145
2022-07-27 15:49:38 -04:00
/// Whether the given [`SymbolId`] is all whitespace according to
/// [`is_xml_whitespace_char`].
///
/// This will first consult the pre-interned whitespace symbol list using
/// [`is_common_whitespace`].
/// If that check fails,
/// it will resort to looking up the symbol and performing a linear scan
/// of the string,
/// terminating early if a non-whitespace character is found.
///
/// Note that the empty string is considered to be whitespace.
#[inline]
fn is_whitespace(sym: SymbolId) -> bool {
// See `sym::prefill`;
// this may require maintenance to keep the prefill list up-to-date
// with common whitespace symbols to avoid symbol lookups.
// This common check is purely a performance optimization.
is_common_whitespace(sym) || {
// If this is called often and is too expensive,
// it may be worth caching metadata about symbols,
// either for XIRF or globally.
// This requires multiple dereferences
// (for looking up the intern for the `SymbolId`,
// which may result in multiple (CPU) cache misses,
// but that would have to be profiled since the symbol may
// have just been interned and may be cached still)
// and then a linear scan of the associated `str`,
// though it will terminate as soon as it finds a non-whitespace
// character.
sym.lookup_str().chars().all(is_xml_whitespace_char)
}
}
impl<const MAX_DEPTH: usize, T, SA> ParseState for XirToXirf<MAX_DEPTH, T, SA>
where
SA: FlatAttrParseState<MAX_DEPTH>,
tamer: Xirf::Text refinement This teaches XIRF to optionally refine Text into RefinedText, which determines whether the given SymbolId represents entirely whitespace. This is something I've been putting off for some time, but now that I'm parsing source language for NIR, it is necessary, in that we can only permit whitespace Text nodes in certain contexts. The idea is to capture the most common whitespace as preinterned symbols. Note that this heuristic ought to be determined from scanning a codebase, which I haven't done yet; this is just an initial list. The fallback is to look up the string associated with the SymbolId and perform a linear scan, aborting on the first non-whitespace character. This combination of checks should be sufficiently performant for now considering that this is only being run on source files, which really are not all that large. (They become large when template-expanded.) I'll optimize further if I notice it show up during profiling. This also frees XIR itself from being concerned by Whitespace. Initially I had used quick-xml's whitespace trimming, but it messed up my span calculations, and those were a pain in the ass to implement to begin with, since I had to resort to pointer arithmetic. I'd rather avoid tweaking it. tameld will not check for whitespace, since it's not important---xmlo files, if malformed, are the fault of the compiler; we can ignore text nodes except in the context of code fragments, where they are never whitespace (unless that's also a compiler bug). Onward and yonward. DEV-7145
2022-07-27 15:49:38 -04:00
T: TextType,
{
type Token = XirToken;
tamer: Xirf::Text refinement This teaches XIRF to optionally refine Text into RefinedText, which determines whether the given SymbolId represents entirely whitespace. This is something I've been putting off for some time, but now that I'm parsing source language for NIR, it is necessary, in that we can only permit whitespace Text nodes in certain contexts. The idea is to capture the most common whitespace as preinterned symbols. Note that this heuristic ought to be determined from scanning a codebase, which I haven't done yet; this is just an initial list. The fallback is to look up the string associated with the SymbolId and perform a linear scan, aborting on the first non-whitespace character. This combination of checks should be sufficiently performant for now considering that this is only being run on source files, which really are not all that large. (They become large when template-expanded.) I'll optimize further if I notice it show up during profiling. This also frees XIR itself from being concerned by Whitespace. Initially I had used quick-xml's whitespace trimming, but it messed up my span calculations, and those were a pain in the ass to implement to begin with, since I had to resort to pointer arithmetic. I'd rather avoid tweaking it. tameld will not check for whitespace, since it's not important---xmlo files, if malformed, are the fault of the compiler; we can ignore text nodes except in the context of code fragments, where they are never whitespace (unless that's also a compiler bug). Onward and yonward. DEV-7145
2022-07-27 15:49:38 -04:00
type Object = XirfToken<T>;
type Error = XirToXirfError;
type Context = StateContext<MAX_DEPTH>;
fn parse_token(
self,
tok: Self::Token,
stack: &mut Self::Context,
) -> TransitionResult<Self> {
use XirToXirf::{AttrExpected, Done, NodeExpected, PreRoot};
match (self, tok) {
// Comments are permitted before and after the first root element.
tamer: Xirf::Text refinement This teaches XIRF to optionally refine Text into RefinedText, which determines whether the given SymbolId represents entirely whitespace. This is something I've been putting off for some time, but now that I'm parsing source language for NIR, it is necessary, in that we can only permit whitespace Text nodes in certain contexts. The idea is to capture the most common whitespace as preinterned symbols. Note that this heuristic ought to be determined from scanning a codebase, which I haven't done yet; this is just an initial list. The fallback is to look up the string associated with the SymbolId and perform a linear scan, aborting on the first non-whitespace character. This combination of checks should be sufficiently performant for now considering that this is only being run on source files, which really are not all that large. (They become large when template-expanded.) I'll optimize further if I notice it show up during profiling. This also frees XIR itself from being concerned by Whitespace. Initially I had used quick-xml's whitespace trimming, but it messed up my span calculations, and those were a pain in the ass to implement to begin with, since I had to resort to pointer arithmetic. I'd rather avoid tweaking it. tameld will not check for whitespace, since it's not important---xmlo files, if malformed, are the fault of the compiler; we can ignore text nodes except in the context of code fragments, where they are never whitespace (unless that's also a compiler bug). Onward and yonward. DEV-7145
2022-07-27 15:49:38 -04:00
(st @ (PreRoot(_) | Done), XirToken::Comment(sym, span)) => {
let depth = Depth(stack.len());
Transition(st).ok(XirfToken::Comment(sym, span, depth))
}
// Ignore whitespace before or after root.
(st @ (PreRoot(_) | Done), XirToken::Text(sym, _))
if is_whitespace(sym) =>
{
Transition(st).incomplete()
tamer: Xirf::Text refinement This teaches XIRF to optionally refine Text into RefinedText, which determines whether the given SymbolId represents entirely whitespace. This is something I've been putting off for some time, but now that I'm parsing source language for NIR, it is necessary, in that we can only permit whitespace Text nodes in certain contexts. The idea is to capture the most common whitespace as preinterned symbols. Note that this heuristic ought to be determined from scanning a codebase, which I haven't done yet; this is just an initial list. The fallback is to look up the string associated with the SymbolId and perform a linear scan, aborting on the first non-whitespace character. This combination of checks should be sufficiently performant for now considering that this is only being run on source files, which really are not all that large. (They become large when template-expanded.) I'll optimize further if I notice it show up during profiling. This also frees XIR itself from being concerned by Whitespace. Initially I had used quick-xml's whitespace trimming, but it messed up my span calculations, and those were a pain in the ass to implement to begin with, since I had to resort to pointer arithmetic. I'd rather avoid tweaking it. tameld will not check for whitespace, since it's not important---xmlo files, if malformed, are the fault of the compiler; we can ignore text nodes except in the context of code fragments, where they are never whitespace (unless that's also a compiler bug). Onward and yonward. DEV-7145
2022-07-27 15:49:38 -04:00
}
(PreRoot(_), tok @ XirToken::Open(..)) => {
Self::parse_node(tok, stack)
tamer: Xirf::Text refinement This teaches XIRF to optionally refine Text into RefinedText, which determines whether the given SymbolId represents entirely whitespace. This is something I've been putting off for some time, but now that I'm parsing source language for NIR, it is necessary, in that we can only permit whitespace Text nodes in certain contexts. The idea is to capture the most common whitespace as preinterned symbols. Note that this heuristic ought to be determined from scanning a codebase, which I haven't done yet; this is just an initial list. The fallback is to look up the string associated with the SymbolId and perform a linear scan, aborting on the first non-whitespace character. This combination of checks should be sufficiently performant for now considering that this is only being run on source files, which really are not all that large. (They become large when template-expanded.) I'll optimize further if I notice it show up during profiling. This also frees XIR itself from being concerned by Whitespace. Initially I had used quick-xml's whitespace trimming, but it messed up my span calculations, and those were a pain in the ass to implement to begin with, since I had to resort to pointer arithmetic. I'd rather avoid tweaking it. tameld will not check for whitespace, since it's not important---xmlo files, if malformed, are the fault of the compiler; we can ignore text nodes except in the context of code fragments, where they are never whitespace (unless that's also a compiler bug). Onward and yonward. DEV-7145
2022-07-27 15:49:38 -04:00
}
tamer: Xirf::Text refinement This teaches XIRF to optionally refine Text into RefinedText, which determines whether the given SymbolId represents entirely whitespace. This is something I've been putting off for some time, but now that I'm parsing source language for NIR, it is necessary, in that we can only permit whitespace Text nodes in certain contexts. The idea is to capture the most common whitespace as preinterned symbols. Note that this heuristic ought to be determined from scanning a codebase, which I haven't done yet; this is just an initial list. The fallback is to look up the string associated with the SymbolId and perform a linear scan, aborting on the first non-whitespace character. This combination of checks should be sufficiently performant for now considering that this is only being run on source files, which really are not all that large. (They become large when template-expanded.) I'll optimize further if I notice it show up during profiling. This also frees XIR itself from being concerned by Whitespace. Initially I had used quick-xml's whitespace trimming, but it messed up my span calculations, and those were a pain in the ass to implement to begin with, since I had to resort to pointer arithmetic. I'd rather avoid tweaking it. tameld will not check for whitespace, since it's not important---xmlo files, if malformed, are the fault of the compiler; we can ignore text nodes except in the context of code fragments, where they are never whitespace (unless that's also a compiler bug). Onward and yonward. DEV-7145
2022-07-27 15:49:38 -04:00
(st @ PreRoot(_), tok) => {
Transition(st).err(XirToXirfError::RootOpenExpected(tok))
}
(NodeExpected, tok) => Self::parse_node(tok, stack),
tamer: Replace ParseStatus::Dead with generic lookahead Oh what a tortured journey. I had originally tried to avoid formalizing lookahead for all parsers by pretending that it was only needed for dead state transitions (that is---states that have no transitions for a given input token), but then I needed to yield information for aggregation. So I added the ability to override the token for `Dead` to yield that, in addition to the token. But then I also needed to yield lookahead for error conditions. It was a mess that didn't make sense. This eliminates `ParseStatus::Dead` entirely and fully integrates the lookahead token in `Parser` that was previously implemented. Notably, the lookahead token is encapsulated in `TransitionResult` and unavailable to `ParseState` implementations, forcing them to rely on `Parser` for recursion. This not only prevents `ParseState` from recursing, but also simplifies delegation by removing the need to manually handle tokens of lookahead. The awkward case here is XIRT, which does not follow the streaming parsing convention, because it was conceived before the parsing framework. It needs to go away, but doing so right now would be a lot of work, so it has to stick around for a little bit longer until the new parser generators can be used instead. It is a persistent thorn in my side, going against the grain. `Parser` will immediately recurse if it sees a token of lookahead with an incomplete parse. This is because stitched parsers will frequently yield a dead state indication when they're done parsing, and there's no use in propagating an `Incomplete` status down the entire lowering pipeline. But, that does mean that the toplevel is not the only thing recursing. _But_, the behavior doesn't really change, in the sense that it would infinitely recurse down the entire lowering stack (though there'd be an opportunity to detect that). This should never happen with a correct parser, but it's not worth the effort right now to try to force such a thing with Rust's type system. Something like TLA+ is better suited here as an aid, but it shouldn't be necessary with clear implementations and proper test cases. Parser generators will also ensure such a thing cannot occur. I had hoped to remove ParseStatus entirely in favor of Parsed, but there's a lot of type inference that happens based on the fact that `ParseStatus` has a `ParseState` type parameter; `Parsed` has only `Object`. It is desirable for a public-facing `Parsed` to not be tied to `ParseState`, since consumers need not be concerned with such a heavy type; however, we _do_ want that heavy type internally, as it carries a lot of useful information that allows for significant and powerful type inference, which in turn creates expressive and convenient APIs. DEV-7145
2022-07-11 23:49:57 -04:00
(AttrExpected(sa), tok) => sa.delegate(
tok,
stack,
|sa| Transition(AttrExpected(sa)),
|| Transition(NodeExpected),
),
(Done, tok) => Transition(Done).dead(tok),
}
}
/// Whether all elements have been closed.
///
/// Parsing will fail if there are any open elements.
/// Intuitively,
/// this means that the parser must have encountered the closing tag
/// for the root element.
fn is_accepting(&self, _: &Self::Context) -> bool {
// TODO: It'd be nice if we could also return additional context to
// aid the user in diagnosing the problem,
// e.g. what element(s) still need closing.
*self == XirToXirf::Done
}
}
tamer: Xirf::Text refinement This teaches XIRF to optionally refine Text into RefinedText, which determines whether the given SymbolId represents entirely whitespace. This is something I've been putting off for some time, but now that I'm parsing source language for NIR, it is necessary, in that we can only permit whitespace Text nodes in certain contexts. The idea is to capture the most common whitespace as preinterned symbols. Note that this heuristic ought to be determined from scanning a codebase, which I haven't done yet; this is just an initial list. The fallback is to look up the string associated with the SymbolId and perform a linear scan, aborting on the first non-whitespace character. This combination of checks should be sufficiently performant for now considering that this is only being run on source files, which really are not all that large. (They become large when template-expanded.) I'll optimize further if I notice it show up during profiling. This also frees XIR itself from being concerned by Whitespace. Initially I had used quick-xml's whitespace trimming, but it messed up my span calculations, and those were a pain in the ass to implement to begin with, since I had to resort to pointer arithmetic. I'd rather avoid tweaking it. tameld will not check for whitespace, since it's not important---xmlo files, if malformed, are the fault of the compiler; we can ignore text nodes except in the context of code fragments, where they are never whitespace (unless that's also a compiler bug). Onward and yonward. DEV-7145
2022-07-27 15:49:38 -04:00
impl<const MAX_DEPTH: usize, T, SA> Display for XirToXirf<MAX_DEPTH, T, SA>
where
SA: FlatAttrParseState<MAX_DEPTH>,
tamer: Xirf::Text refinement This teaches XIRF to optionally refine Text into RefinedText, which determines whether the given SymbolId represents entirely whitespace. This is something I've been putting off for some time, but now that I'm parsing source language for NIR, it is necessary, in that we can only permit whitespace Text nodes in certain contexts. The idea is to capture the most common whitespace as preinterned symbols. Note that this heuristic ought to be determined from scanning a codebase, which I haven't done yet; this is just an initial list. The fallback is to look up the string associated with the SymbolId and perform a linear scan, aborting on the first non-whitespace character. This combination of checks should be sufficiently performant for now considering that this is only being run on source files, which really are not all that large. (They become large when template-expanded.) I'll optimize further if I notice it show up during profiling. This also frees XIR itself from being concerned by Whitespace. Initially I had used quick-xml's whitespace trimming, but it messed up my span calculations, and those were a pain in the ass to implement to begin with, since I had to resort to pointer arithmetic. I'd rather avoid tweaking it. tameld will not check for whitespace, since it's not important---xmlo files, if malformed, are the fault of the compiler; we can ignore text nodes except in the context of code fragments, where they are never whitespace (unless that's also a compiler bug). Onward and yonward. DEV-7145
2022-07-27 15:49:38 -04:00
T: TextType,
{
fn fmt(&self, f: &mut std::fmt::Formatter) -> std::fmt::Result {
use XirToXirf::*;
match self {
tamer: Xirf::Text refinement This teaches XIRF to optionally refine Text into RefinedText, which determines whether the given SymbolId represents entirely whitespace. This is something I've been putting off for some time, but now that I'm parsing source language for NIR, it is necessary, in that we can only permit whitespace Text nodes in certain contexts. The idea is to capture the most common whitespace as preinterned symbols. Note that this heuristic ought to be determined from scanning a codebase, which I haven't done yet; this is just an initial list. The fallback is to look up the string associated with the SymbolId and perform a linear scan, aborting on the first non-whitespace character. This combination of checks should be sufficiently performant for now considering that this is only being run on source files, which really are not all that large. (They become large when template-expanded.) I'll optimize further if I notice it show up during profiling. This also frees XIR itself from being concerned by Whitespace. Initially I had used quick-xml's whitespace trimming, but it messed up my span calculations, and those were a pain in the ass to implement to begin with, since I had to resort to pointer arithmetic. I'd rather avoid tweaking it. tameld will not check for whitespace, since it's not important---xmlo files, if malformed, are the fault of the compiler; we can ignore text nodes except in the context of code fragments, where they are never whitespace (unless that's also a compiler bug). Onward and yonward. DEV-7145
2022-07-27 15:49:38 -04:00
PreRoot(_) => write!(f, "expecting document root"),
NodeExpected => write!(f, "expecting a node"),
AttrExpected(sa) => Display::fmt(sa, f),
Done => write!(f, "done parsing document root"),
}
}
}
tamer: Xirf::Text refinement This teaches XIRF to optionally refine Text into RefinedText, which determines whether the given SymbolId represents entirely whitespace. This is something I've been putting off for some time, but now that I'm parsing source language for NIR, it is necessary, in that we can only permit whitespace Text nodes in certain contexts. The idea is to capture the most common whitespace as preinterned symbols. Note that this heuristic ought to be determined from scanning a codebase, which I haven't done yet; this is just an initial list. The fallback is to look up the string associated with the SymbolId and perform a linear scan, aborting on the first non-whitespace character. This combination of checks should be sufficiently performant for now considering that this is only being run on source files, which really are not all that large. (They become large when template-expanded.) I'll optimize further if I notice it show up during profiling. This also frees XIR itself from being concerned by Whitespace. Initially I had used quick-xml's whitespace trimming, but it messed up my span calculations, and those were a pain in the ass to implement to begin with, since I had to resort to pointer arithmetic. I'd rather avoid tweaking it. tameld will not check for whitespace, since it's not important---xmlo files, if malformed, are the fault of the compiler; we can ignore text nodes except in the context of code fragments, where they are never whitespace (unless that's also a compiler bug). Onward and yonward. DEV-7145
2022-07-27 15:49:38 -04:00
impl<const MAX_DEPTH: usize, T, SA> XirToXirf<MAX_DEPTH, T, SA>
where
SA: FlatAttrParseState<MAX_DEPTH>,
tamer: Xirf::Text refinement This teaches XIRF to optionally refine Text into RefinedText, which determines whether the given SymbolId represents entirely whitespace. This is something I've been putting off for some time, but now that I'm parsing source language for NIR, it is necessary, in that we can only permit whitespace Text nodes in certain contexts. The idea is to capture the most common whitespace as preinterned symbols. Note that this heuristic ought to be determined from scanning a codebase, which I haven't done yet; this is just an initial list. The fallback is to look up the string associated with the SymbolId and perform a linear scan, aborting on the first non-whitespace character. This combination of checks should be sufficiently performant for now considering that this is only being run on source files, which really are not all that large. (They become large when template-expanded.) I'll optimize further if I notice it show up during profiling. This also frees XIR itself from being concerned by Whitespace. Initially I had used quick-xml's whitespace trimming, but it messed up my span calculations, and those were a pain in the ass to implement to begin with, since I had to resort to pointer arithmetic. I'd rather avoid tweaking it. tameld will not check for whitespace, since it's not important---xmlo files, if malformed, are the fault of the compiler; we can ignore text nodes except in the context of code fragments, where they are never whitespace (unless that's also a compiler bug). Onward and yonward. DEV-7145
2022-07-27 15:49:38 -04:00
T: TextType,
{
/// Parse a token while in a state expecting a node.
fn parse_node(
tok: <Self as ParseState>::Token,
stack: &mut ElementStack<MAX_DEPTH>,
) -> TransitionResult<Self> {
use XirToXirf::{AttrExpected, Done, NodeExpected};
let depth = Depth(stack.len());
match tok {
XirToken::Open(qname, span) if stack.len() == MAX_DEPTH => {
Transition(NodeExpected).err(XirToXirfError::MaxDepthExceeded {
tamer: xir: Introduce {Ele,Open,Close}Span This isn't conceptally all that significant of a change, but there was a lot of modify to get it working. I would generally separate this into a commit for the implementation and another commit for the integration, but I decided to keep things together. This serves a role similar to AttrSpan---this allows deriving a span representing the element name from a span representing the entire XIR token. This will provide more useful context for errors---including the tag delimiter(s) means that we care about the fact that an element is in that position (as opposed to some other type of node) within the context of an error. However, if we are expecting an element but take issue with the element name itself, we want to place emphasis on that instead. This also starts to consider the issue of span contexts---a blob of detached data that is `Span` is useful for error context, but it's not useful for manipulation or deriving additional information. For that, we need to encode additional context, and this is an attempt at that. I am interested in the concept of providing Spans that are guaranteed to actually make sense---that are instantiated and manipulated with APIs that ensure consistency. But such a thing buys us very little, practically speaking, over what I have now for TAMER, and so I don't expect to actually implement that for this project; I'll leave that for a personal project. TAMER's already take a lot of my personal interests and it can cause me a lot of grief sometimes (with regards to letting my aspirations cause me more work). DEV-7145
2022-06-24 13:51:49 -04:00
open: (qname, span.tag_span()),
max: Depth(MAX_DEPTH),
})
}
XirToken::Open(qname, span) => {
tamer: xir: Introduce {Ele,Open,Close}Span This isn't conceptally all that significant of a change, but there was a lot of modify to get it working. I would generally separate this into a commit for the implementation and another commit for the integration, but I decided to keep things together. This serves a role similar to AttrSpan---this allows deriving a span representing the element name from a span representing the entire XIR token. This will provide more useful context for errors---including the tag delimiter(s) means that we care about the fact that an element is in that position (as opposed to some other type of node) within the context of an error. However, if we are expecting an element but take issue with the element name itself, we want to place emphasis on that instead. This also starts to consider the issue of span contexts---a blob of detached data that is `Span` is useful for error context, but it's not useful for manipulation or deriving additional information. For that, we need to encode additional context, and this is an attempt at that. I am interested in the concept of providing Spans that are guaranteed to actually make sense---that are instantiated and manipulated with APIs that ensure consistency. But such a thing buys us very little, practically speaking, over what I have now for TAMER, and so I don't expect to actually implement that for this project; I'll leave that for a personal project. TAMER's already take a lot of my personal interests and it can cause me a lot of grief sometimes (with regards to letting my aspirations cause me more work). DEV-7145
2022-06-24 13:51:49 -04:00
stack.push((qname, span.tag_span()));
// Delegate to the attribute parser until it is complete.
Transition(AttrExpected(SA::default()))
.ok(XirfToken::Open(qname, span, depth))
}
XirToken::Close(close_oqname, close_span) => {
match (close_oqname, stack.pop()) {
(_, None) => unreachable!("parser should be in Done state"),
(Some(qname), Some((open_qname, open_span)))
if qname != open_qname =>
{
Transition(NodeExpected).err(
XirToXirfError::UnbalancedTag {
open: (open_qname, open_span),
tamer: xir: Introduce {Ele,Open,Close}Span This isn't conceptally all that significant of a change, but there was a lot of modify to get it working. I would generally separate this into a commit for the implementation and another commit for the integration, but I decided to keep things together. This serves a role similar to AttrSpan---this allows deriving a span representing the element name from a span representing the entire XIR token. This will provide more useful context for errors---including the tag delimiter(s) means that we care about the fact that an element is in that position (as opposed to some other type of node) within the context of an error. However, if we are expecting an element but take issue with the element name itself, we want to place emphasis on that instead. This also starts to consider the issue of span contexts---a blob of detached data that is `Span` is useful for error context, but it's not useful for manipulation or deriving additional information. For that, we need to encode additional context, and this is an attempt at that. I am interested in the concept of providing Spans that are guaranteed to actually make sense---that are instantiated and manipulated with APIs that ensure consistency. But such a thing buys us very little, practically speaking, over what I have now for TAMER, and so I don't expect to actually implement that for this project; I'll leave that for a personal project. TAMER's already take a lot of my personal interests and it can cause me a lot of grief sometimes (with regards to letting my aspirations cause me more work). DEV-7145
2022-06-24 13:51:49 -04:00
close: (qname, close_span.tag_span()),
},
)
}
// Final closing tag (for root node) completes the document.
tamer: Xirf::Text refinement This teaches XIRF to optionally refine Text into RefinedText, which determines whether the given SymbolId represents entirely whitespace. This is something I've been putting off for some time, but now that I'm parsing source language for NIR, it is necessary, in that we can only permit whitespace Text nodes in certain contexts. The idea is to capture the most common whitespace as preinterned symbols. Note that this heuristic ought to be determined from scanning a codebase, which I haven't done yet; this is just an initial list. The fallback is to look up the string associated with the SymbolId and perform a linear scan, aborting on the first non-whitespace character. This combination of checks should be sufficiently performant for now considering that this is only being run on source files, which really are not all that large. (They become large when template-expanded.) I'll optimize further if I notice it show up during profiling. This also frees XIR itself from being concerned by Whitespace. Initially I had used quick-xml's whitespace trimming, but it messed up my span calculations, and those were a pain in the ass to implement to begin with, since I had to resort to pointer arithmetic. I'd rather avoid tweaking it. tameld will not check for whitespace, since it's not important---xmlo files, if malformed, are the fault of the compiler; we can ignore text nodes except in the context of code fragments, where they are never whitespace (unless that's also a compiler bug). Onward and yonward. DEV-7145
2022-07-27 15:49:38 -04:00
(..) if stack.len() == 0 => Transition(Done).ok(
XirfToken::Close(close_oqname, close_span, Depth(0)),
),
(..) => {
let depth = stack.len();
tamer: Xirf::Text refinement This teaches XIRF to optionally refine Text into RefinedText, which determines whether the given SymbolId represents entirely whitespace. This is something I've been putting off for some time, but now that I'm parsing source language for NIR, it is necessary, in that we can only permit whitespace Text nodes in certain contexts. The idea is to capture the most common whitespace as preinterned symbols. Note that this heuristic ought to be determined from scanning a codebase, which I haven't done yet; this is just an initial list. The fallback is to look up the string associated with the SymbolId and perform a linear scan, aborting on the first non-whitespace character. This combination of checks should be sufficiently performant for now considering that this is only being run on source files, which really are not all that large. (They become large when template-expanded.) I'll optimize further if I notice it show up during profiling. This also frees XIR itself from being concerned by Whitespace. Initially I had used quick-xml's whitespace trimming, but it messed up my span calculations, and those were a pain in the ass to implement to begin with, since I had to resort to pointer arithmetic. I'd rather avoid tweaking it. tameld will not check for whitespace, since it's not important---xmlo files, if malformed, are the fault of the compiler; we can ignore text nodes except in the context of code fragments, where they are never whitespace (unless that's also a compiler bug). Onward and yonward. DEV-7145
2022-07-27 15:49:38 -04:00
Transition(NodeExpected).ok(XirfToken::Close(
close_oqname,
close_span,
Depth(depth),
))
}
}
}
XirToken::Comment(sym, span) => Transition(NodeExpected)
.ok(XirfToken::Comment(sym, span, depth)),
tamer: Xirf::Text refinement This teaches XIRF to optionally refine Text into RefinedText, which determines whether the given SymbolId represents entirely whitespace. This is something I've been putting off for some time, but now that I'm parsing source language for NIR, it is necessary, in that we can only permit whitespace Text nodes in certain contexts. The idea is to capture the most common whitespace as preinterned symbols. Note that this heuristic ought to be determined from scanning a codebase, which I haven't done yet; this is just an initial list. The fallback is to look up the string associated with the SymbolId and perform a linear scan, aborting on the first non-whitespace character. This combination of checks should be sufficiently performant for now considering that this is only being run on source files, which really are not all that large. (They become large when template-expanded.) I'll optimize further if I notice it show up during profiling. This also frees XIR itself from being concerned by Whitespace. Initially I had used quick-xml's whitespace trimming, but it messed up my span calculations, and those were a pain in the ass to implement to begin with, since I had to resort to pointer arithmetic. I'd rather avoid tweaking it. tameld will not check for whitespace, since it's not important---xmlo files, if malformed, are the fault of the compiler; we can ignore text nodes except in the context of code fragments, where they are never whitespace (unless that's also a compiler bug). Onward and yonward. DEV-7145
2022-07-27 15:49:38 -04:00
XirToken::Text(sym, span) => Transition(NodeExpected)
.ok(XirfToken::Text(T::from(Text(sym, span)), depth)),
XirToken::CData(sym, span) => {
Transition(NodeExpected).ok(XirfToken::CData(sym, span, depth))
}
// We should transition to `State::Attr` before encountering any
// of these tokens.
XirToken::AttrName(..)
| XirToken::AttrValue(..)
Revert "tamer: xir: Initial re-introduction of AttrEnd" This reverts commit b973d36862a4a2aaf53fb0b25fba01b57e5a7463. Alright, I'm getting sick of fighting with myself on this. But rather than just removing the last commit, I'm going to keep it around, so that my thoughts are clearly documented for my future quarrels with myself. Firstly: this added more overhead than I wanted it to. While it wasn't significant, it did add 100--150ms to one of our largest systems, up from ~2.8s, which seems a bit much for a token that's really just meant to make life easier for the parser. Further, it seems that all I've managed to do is push my original problem to a different layer---this started as a means to resolve having to emit both an object and an error simultaneously in the case where aggregate attribute parsing has completed, but we encounter an error on the next token (e.g. an unexpected element). But XIRF, if it's missing AttrEnd, should throw an error, but should also recover. Recovery is easy---just assume that it was present---_but then we don't emit a XIRF `AttrEnd` token_, which is necessary for downstream systems. So we'd need to either: (a) emit both a token and an error; or (b) panic. But if we're doing (a), then the need for `AttrEnd` goes away, because it solves the original problem (though the other concerns of the previous commit still stand). (b) is not ideal at all, even though the missing token does represent an internal system error; it's not something the user can correct. But, given that it's something that the user cannot correct, doesn't that imply that it's an awkward thing to include in the token stream? So back to `AttrEnd` being an awkward PITA to have. So, given (a), I'll just do that: errors will become more of a "hey, this error just occurred, but I'm trying to recover---here's an object that you should use if you choose to continue parsing, but it may or may not be what you're looking for; proceed with caution". That flips the original script: I imagined having external systems feed recovery tokens, but this encapsulates recovery within the parser, which really is more appropriate, though less flexible than having an omniscient external recovery system; such a monolith was always an awkward concept and would be difficult to implement cleanly. This can also potentially be implemented as a generalization of the Dead state change that allowed an object to be emitted alongside the lookahead/error. Anyway, back to where I was...I'm sure I'll look back on this in the future shaking my head, reflecting on how naive I was. DEV-7145
2022-06-29 11:02:18 -04:00
| XirToken::AttrValueFragment(..) => {
unreachable!("attribute token in NodeExpected state: {tok:?}")
}
}
}
}
/// Produce a streaming parser lowering a XIR [`TokenStream`] into a XIRF
/// stream.
tamer: Xirf::Text refinement This teaches XIRF to optionally refine Text into RefinedText, which determines whether the given SymbolId represents entirely whitespace. This is something I've been putting off for some time, but now that I'm parsing source language for NIR, it is necessary, in that we can only permit whitespace Text nodes in certain contexts. The idea is to capture the most common whitespace as preinterned symbols. Note that this heuristic ought to be determined from scanning a codebase, which I haven't done yet; this is just an initial list. The fallback is to look up the string associated with the SymbolId and perform a linear scan, aborting on the first non-whitespace character. This combination of checks should be sufficiently performant for now considering that this is only being run on source files, which really are not all that large. (They become large when template-expanded.) I'll optimize further if I notice it show up during profiling. This also frees XIR itself from being concerned by Whitespace. Initially I had used quick-xml's whitespace trimming, but it messed up my span calculations, and those were a pain in the ass to implement to begin with, since I had to resort to pointer arithmetic. I'd rather avoid tweaking it. tameld will not check for whitespace, since it's not important---xmlo files, if malformed, are the fault of the compiler; we can ignore text nodes except in the context of code fragments, where they are never whitespace (unless that's also a compiler bug). Onward and yonward. DEV-7145
2022-07-27 15:49:38 -04:00
pub fn parse<const MAX_DEPTH: usize, T: TextType>(
toks: impl TokenStream,
tamer: Xirf::Text refinement This teaches XIRF to optionally refine Text into RefinedText, which determines whether the given SymbolId represents entirely whitespace. This is something I've been putting off for some time, but now that I'm parsing source language for NIR, it is necessary, in that we can only permit whitespace Text nodes in certain contexts. The idea is to capture the most common whitespace as preinterned symbols. Note that this heuristic ought to be determined from scanning a codebase, which I haven't done yet; this is just an initial list. The fallback is to look up the string associated with the SymbolId and perform a linear scan, aborting on the first non-whitespace character. This combination of checks should be sufficiently performant for now considering that this is only being run on source files, which really are not all that large. (They become large when template-expanded.) I'll optimize further if I notice it show up during profiling. This also frees XIR itself from being concerned by Whitespace. Initially I had used quick-xml's whitespace trimming, but it messed up my span calculations, and those were a pain in the ass to implement to begin with, since I had to resort to pointer arithmetic. I'd rather avoid tweaking it. tameld will not check for whitespace, since it's not important---xmlo files, if malformed, are the fault of the compiler; we can ignore text nodes except in the context of code fragments, where they are never whitespace (unless that's also a compiler bug). Onward and yonward. DEV-7145
2022-07-27 15:49:38 -04:00
) -> impl Iterator<Item = ParsedResult<XirToXirf<MAX_DEPTH, T>>> {
XirToXirf::<MAX_DEPTH, T>::parse(toks)
}
/// Parsing error from [`XirToXirf`].
#[derive(Debug, Eq, PartialEq)]
pub enum XirToXirfError {
/// Opening root element tag was expected.
RootOpenExpected(XirToken),
/// Opening tag exceeds the maximum nesting depth for this parser.
MaxDepthExceeded { open: (QName, Span), max: Depth },
/// The closing tag does not match the opening tag at the same level of
/// nesting.
UnbalancedTag {
open: (QName, Span),
close: (QName, Span),
},
/// Error from the attribute parser.
AttrError(AttrParseError),
}
impl Display for XirToXirfError {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
use XirToXirfError::*;
match self {
RootOpenExpected(_tok) => {
write!(f, "missing opening root element",)
}
MaxDepthExceeded {
open: (_name, _),
max,
} => {
write!(
f,
"maximum XML element nesting depth of `{max}` exceeded"
)
}
UnbalancedTag {
open: (open_name, _),
close: (_close_name, _),
} => {
write!(f, "expected closing tag for `{open_name}`")
}
AttrError(e) => Display::fmt(e, f),
}
}
}
impl Error for XirToXirfError {
fn source(&self) -> Option<&(dyn Error + 'static)> {
match self {
Self::AttrError(e) => Some(e),
_ => None,
}
}
}
impl Diagnostic for XirToXirfError {
fn describe(&self) -> Vec<AnnotatedSpan> {
use XirToXirfError::*;
match self {
RootOpenExpected(tok) => {
// TODO: Should the span be the first byte,
// or should we delegate that question to an e.g. `SpanLike`?
tok.span()
.error("an opening root node was expected here")
.into()
}
MaxDepthExceeded {
open: (_, span),
max,
} => span
.error(format!(
"this opening tag increases the level of nesting \
past the limit of {max}"
))
.into(),
UnbalancedTag {
open: (open_name, open_span),
close: (_close_name, close_span),
} => {
// TODO: hint saying that the nesting could be wrong, etc;
// we can't just suggest a replacement,
// since that's not necessarily the problem
vec![
open_span
.note(format!("element `{open_name}` is opened here")),
// No need to state the close name since the source line
// will be highlighted by the diagnostic message.
close_span.error(format!("expected `</{open_name}>`")),
]
}
AttrError(e) => e.describe(),
}
}
}
impl From<AttrParseError> for XirToXirfError {
fn from(e: AttrParseError) -> Self {
Self::AttrError(e)
}
}
#[cfg(test)]
tamer: xir: Introduce {Ele,Open,Close}Span This isn't conceptally all that significant of a change, but there was a lot of modify to get it working. I would generally separate this into a commit for the implementation and another commit for the integration, but I decided to keep things together. This serves a role similar to AttrSpan---this allows deriving a span representing the element name from a span representing the entire XIR token. This will provide more useful context for errors---including the tag delimiter(s) means that we care about the fact that an element is in that position (as opposed to some other type of node) within the context of an error. However, if we are expecting an element but take issue with the element name itself, we want to place emphasis on that instead. This also starts to consider the issue of span contexts---a blob of detached data that is `Span` is useful for error context, but it's not useful for manipulation or deriving additional information. For that, we need to encode additional context, and this is an attempt at that. I am interested in the concept of providing Spans that are guaranteed to actually make sense---that are instantiated and manipulated with APIs that ensure consistency. But such a thing buys us very little, practically speaking, over what I have now for TAMER, and so I don't expect to actually implement that for this project; I'll leave that for a personal project. TAMER's already take a lot of my personal interests and it can cause me a lot of grief sometimes (with regards to letting my aspirations cause me more work). DEV-7145
2022-06-24 13:51:49 -04:00
pub mod test;