From e17f2d68765a0661478572a098ffdf6f1bd3d669 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?cel=20=F0=9F=8C=B8?= Date: Mon, 11 Nov 2024 13:46:04 +0000 Subject: [PATCH] add non-streaming parsers --- src/xml/mod.rs | 1 + src/xml/parsers_complete.rs | 1522 +++++++++++++++++++++++++++++++++++ 2 files changed, 1523 insertions(+) create mode 100644 src/xml/parsers_complete.rs diff --git a/src/xml/mod.rs b/src/xml/mod.rs index 0e84155..2d20ca0 100644 --- a/src/xml/mod.rs +++ b/src/xml/mod.rs @@ -4,6 +4,7 @@ use crate::error::Error; pub mod composers; pub mod parsers; +pub mod parsers_complete; /// [1] NSAttName ::= PrefixedAttName | DefaultAttName #[derive(Clone, Debug)] diff --git a/src/xml/parsers_complete.rs b/src/xml/parsers_complete.rs new file mode 100644 index 0000000..fff8bf2 --- /dev/null +++ b/src/xml/parsers_complete.rs @@ -0,0 +1,1522 @@ +use nom::{ + branch::alt, + bytes::complete::{is_a, is_not, tag, take, take_while}, + character::complete::{char, none_of, one_of, satisfy}, + combinator::{map, not, opt, peek, recognize, value}, + error::{Error, ErrorKind}, + multi::{many0, many1, many_till}, + sequence::{delimited, pair, preceded, separated_pair, terminated, tuple}, + Err, IResult, Parser as NomParser, +}; + +use crate::xml::NSAttName; + +use super::{ + AttDef, AttDefName, AttType, AttValue, AttValueData, AttlistDecl, Attribute, CDEnd, CDSect, + CDStart, CData, Char, CharData, CharRef, Children, ChildrenKind, Choice, Comment, + ConditionalSect, Content, ContentItem, Contentspec, Cp, CpKind, DeclSep, DefaultAttName, + DefaultDecl, DoctypeDecl, Document, ETag, Element, Elementdecl, EmptyElemTag, EncName, + EncodingDecl, EntityDecl, EntityDef, EntityRef, EntityValue, EntityValueData, EnumeratedType, + Enumeration, Eq, ExtParsedEnt, ExtSubset, ExtSubsetDecl, ExtSubsetDeclaration, ExternalID, + GEDecl, Ignore, IgnoreSect, IgnoreSectContents, IncludeSect, IntSubset, IntSubsetDeclaration, + LocalPart, MarkupDecl, Misc, Mixed, NCName, NDataDecl, Name, NameChar, NameStartChar, Names, + Nmtoken, Nmtokens, NotationDecl, NotationDeclID, NotationType, Occurence, PEDecl, PEDef, + PEReference, PITarget, Prefix, PrefixedAttName, PrefixedName, Prolog, PubidChar, PubidLiteral, + PublicID, QName, Reference, SDDecl, STag, Seq, StringType, SystemLiteral, TextDecl, + TokenizedType, UnprefixedName, VersionInfo, VersionNum, XMLDecl, PI, S, +}; + +pub trait Parser<'s, T> { + fn parse(input: &'s str) -> IResult<&str, T>; +} + +/// [1] NSAttName ::= PrefixedAttName | DefaultAttName +impl<'s> Parser<'s, NSAttName<'s>> for NSAttName<'s> { + fn parse(input: &'s str) -> IResult<&str, NSAttName<'s>> { + alt(( + map(PrefixedAttName::parse, |prefixed_att_name| { + NSAttName::PrefixedAttName(prefixed_att_name) + }), + value(NSAttName::DefaultAttName, DefaultAttName::parse), + ))(input) + } +} + +/// [2] PrefixedAttName ::= 'xmlns:' NCName +impl<'s> Parser<'s, PrefixedAttName<'s>> for PrefixedAttName<'s> { + fn parse(input: &'s str) -> IResult<&str, PrefixedAttName<'s>> { + map(preceded(tag("xmlns:"), NCName::parse), |nc_name| { + PrefixedAttName(nc_name) + })(input) + } +} + +/// [3] DefaultAttName ::= 'xmlns'; +impl Parser<'_, DefaultAttName> for DefaultAttName { + fn parse(input: &str) -> IResult<&str, DefaultAttName> { + value(DefaultAttName, tag("xmlns"))(input) + } +} + +/// [5] Name ::= NameStartChar (NameChar)* +/// [4] NCName ::= Name - (Char* ':' Char*) +impl<'s> Parser<'s, NCName<'s>> for NCName<'s> { + fn parse(input: &'s str) -> IResult<&str, NCName<'s>> { + let (rest, name) = peek(recognize(Name::parse))(input)?; + if let Some(char) = name.find(':') { + map(take(char), |nc_name| NCName(nc_name))(input) + } else { + map(recognize(Name::parse), |nc_name| NCName(nc_name))(input) + } + } +} + +/// [7] QName ::= PrefixedName | UnprefixedName +impl<'s> Parser<'s, QName<'s>> for QName<'s> { + fn parse(input: &'s str) -> IResult<&str, QName<'s>> { + alt(( + map(PrefixedName::parse, |prefixed_name| { + QName::PrefixedName(prefixed_name) + }), + map(UnprefixedName::parse, |unprefixed_name| { + QName::UnprefixedName(unprefixed_name) + }), + ))(input) + } +} + +/// [8] PrefixedName ::= Prefix ':' LocalPart +impl<'s> Parser<'s, PrefixedName<'s>> for PrefixedName<'s> { + fn parse(input: &'s str) -> IResult<&str, PrefixedName<'s>> { + map( + separated_pair(Prefix::parse, char(':'), LocalPart::parse), + |(prefix, local_part)| PrefixedName { prefix, local_part }, + )(input) + } +} + +/// [9] UnprefixedName ::= LocalPart +impl<'s> Parser<'s, UnprefixedName<'s>> for UnprefixedName<'s> { + fn parse(input: &'s str) -> IResult<&str, UnprefixedName<'s>> { + map(LocalPart::parse, |local_part| UnprefixedName(local_part))(input) + } +} + +/// [10] Prefix ::= NCName +impl<'s> Parser<'s, Prefix<'s>> for Prefix<'s> { + fn parse(input: &'s str) -> IResult<&str, Prefix<'s>> { + map(NCName::parse, |nc_name| Prefix(nc_name))(input) + } +} + +/// [11] LocalPart ::= NCName +impl<'s> Parser<'s, LocalPart<'s>> for LocalPart<'s> { + fn parse(input: &'s str) -> IResult<&str, LocalPart<'s>> { + map(NCName::parse, |nc_name| LocalPart(nc_name))(input) + } +} + +// xml spec + +/// [1] document ::= prolog element Misc* +impl<'s> Parser<'s, Document<'s>> for Document<'s> { + fn parse(input: &'s str) -> IResult<&str, Document<'s>> { + tuple((Prolog::parse, Element::parse, many0(Misc::parse)))(input) + } +} + +/// [2] Char ::= #x9 | #xA | #xD | [#x20-#xD7FF] | [#xE000-#xFFFD] | [#x10000-#x10FFFF] /* any Unicode character, excluding the surrogate blocks, FFFE, and FFFF. */ +impl Parser<'_, Char> for Char { + fn parse(input: &str) -> IResult<&str, Char> { + map( + satisfy( + |c| matches!(c, '\u{9}' | '\u{A}' | '\u{D}' | '\u{20}'..='\u{D7FF}' | '\u{E000}'..='\u{FFFD}' | '\u{10000}'..='\u{10FFFF}'), + ), + |char| Char(char), + )(input) + } +} + +/// [3] S ::= (#x20 | #x9 | #xD | #xA)+ +impl Parser<'_, S> for S { + fn parse(input: &str) -> IResult<&str, S> { + // TODO?: whitespacing + // map(is_a("\u{20}\u{9}\u{D}\u{A}"), |s| S(s))(input) + value(S, is_a("\u{20}\u{9}\u{D}\u{A}"))(input) + } +} + +/// [4] NameStartChar ::= ":" | [A-Z] | "_" | [a-z] | [#xC0-#xD6] | [#xD8-#xF6] | [#xF8-#x2FF] | [#x370-#x37D] | [#x37F-#x1FFF] | [#x200C-#x200D] | [#x2070-#x218F] | [#x2C00-#x2FEF] | [#x3001-#xD7FF] | [#xF900-#xFDCF] | [#xFDF0-#xFFFD] | [#x10000-#xEFFFF] +impl Parser<'_, NameStartChar> for NameStartChar { + fn parse(input: &str) -> IResult<&str, NameStartChar> { + map( + satisfy( + |c| matches!(c, ':' | 'A'..='Z' | '_' | 'a'..='z' | '\u{C0}'..='\u{D6}' | '\u{D8}'..='\u{F6}' | '\u{F8}'..='\u{2FF}' | '\u{370}'..='\u{37D}' | '\u{37F}'..='\u{1FFF}' | '\u{200C}'..='\u{200D}' | '\u{2070}'..='\u{218F}' | '\u{2C00}'..='\u{2FEF}' | '\u{3001}'..='\u{D7FF}' | '\u{F900}'..='\u{FDCF}' | '\u{FDF0}'..='\u{FFFD}' | '\u{10000}'..='\u{EFFFF}'), + ), + |c| NameStartChar(c), + )(input) + } +} + +/// [4a] NameChar ::= NameStartChar | "-" | "." | [0-9] | #xB7 | [#x0300-#x036F] | [#x203F-#x2040] +impl Parser<'_, NameChar> for NameChar { + fn parse(input: &str) -> IResult<&str, NameChar> { + map( + alt(( + map(NameStartChar::parse, |NameStartChar(c)| c), + satisfy( + |c| matches!(c, '-' | '.' | '0'..='9' | '\u{B7}' | '\u{0300}'..='\u{036F}' | '\u{203F}'..='\u{2040}'), + ), + )), + |c| NameChar(c), + )(input) + } +} + +/// [5] Name ::= NameStartChar (NameChar)* +impl<'s> Parser<'s, Name<'s>> for Name<'s> { + fn parse(input: &'s str) -> IResult<&str, Name<'s>> { + map( + recognize(pair(NameStartChar::parse, many0(NameChar::parse))), + |name| Name(name), + )(input) + } +} + +/// [6] Names ::= Name (#x20 Name)* +impl<'s> Parser<'s, Names<'s>> for Names<'s> { + // TODO: fix + fn parse(input: &'s str) -> IResult<&str, Names<'s>> { + map( + pair(Name::parse, many0(preceded(char('\u{20}'), Name::parse))), + |(head, tail)| Names(vec![vec![head], tail].concat()), + )(input) + } +} + +/// [7] Nmtoken ::= (NameChar)+ +impl<'s> Parser<'s, Nmtoken<'s>> for Nmtoken<'s> { + fn parse(input: &'s str) -> IResult<&str, Nmtoken<'s>> { + map(recognize(many1(NameChar::parse)), |nmtoken| { + Nmtoken(nmtoken) + })(input) + } +} + +/// [8] Nmtokens ::= Nmtoken (#x20 Nmtoken)* +impl<'s> Parser<'s, Nmtokens<'s>> for Nmtokens<'s> { + fn parse(input: &'s str) -> IResult<&str, Nmtokens<'s>> { + map( + pair( + Nmtoken::parse, + many0(preceded(char('\u{20}'), Nmtoken::parse)), + ), + |(head, tail)| Nmtokens(vec![vec![head], tail].concat()), + )(input) + } +} + +/// [9] EntityValue ::= '"' ([^%&"] | PEReference | Reference)* '"' +/// | "'" ([^%&'] | PEReference | Reference)* "'" +impl<'s> Parser<'s, EntityValue<'s>> for EntityValue<'s> { + fn parse(input: &'s str) -> IResult<&str, EntityValue<'s>> { + alt(( + map( + delimited( + char('"'), + many0(alt(( + map( + recognize(many_till(take(1usize), peek(one_of("%&\"")))), + |string| EntityValueData::String(string), + ), + map(PEReference::parse, |pe_reference| { + EntityValueData::PEReference(pe_reference) + }), + map(Reference::parse, |reference| { + EntityValueData::Reference(reference) + }), + ))), + char('"'), + ), + |entity_value| EntityValue::DoubleQuoted(entity_value), + ), + map( + delimited( + char('\''), + many0(alt(( + map( + recognize(many_till(take(1usize), peek(one_of("%&'")))), + |string| EntityValueData::String(string), + ), + map(PEReference::parse, |pe_reference| { + EntityValueData::PEReference(pe_reference) + }), + map(Reference::parse, |reference| { + EntityValueData::Reference(reference) + }), + ))), + char('\''), + ), + |entity_value| EntityValue::SingleQuoted(entity_value), + ), + ))(input) + } +} + +/// [10] AttValue ::= '"' ([^<&"] | Reference)* '"' +/// | "'" ([^<&'] | Reference)* "'" +impl<'s> Parser<'s, AttValue<'s>> for AttValue<'s> { + fn parse(input: &'s str) -> IResult<&str, AttValue<'s>> { + alt(( + map( + delimited( + char('"'), + many0(alt(( + map(is_not("<&\""), |string| AttValueData::String(string)), + map(Reference::parse, |reference| { + AttValueData::Reference(reference) + }), + ))), + char('"'), + ), + |att_value| AttValue::DoubleQuoted(att_value), + ), + map( + delimited( + char('\''), + many0(alt(( + map(is_not("<&'"), |string| AttValueData::String(string)), + map(Reference::parse, |reference| { + AttValueData::Reference(reference) + }), + ))), + char('\''), + ), + |att_value| AttValue::SingleQuoted(att_value), + ), + ))(input) + } +} + +/// [11] SystemLiteral ::= ('"' [^"]* '"') | ("'" [^']* "'") +impl<'s> Parser<'s, SystemLiteral<'s>> for SystemLiteral<'s> { + fn parse(input: &'s str) -> IResult<&str, SystemLiteral<'s>> { + alt(( + map( + delimited(char('"'), recognize(many0(none_of("\""))), char('"')), + |system_literal| SystemLiteral::DoubleQuoted(system_literal), + ), + map( + delimited(char('\''), recognize(many0(none_of("'"))), char('\'')), + |system_literal| SystemLiteral::SingleQuoted(system_literal), + ), + ))(input) + } +} + +/// [12] PubidLiteral ::= '"' PubidChar* '"' | "'" (PubidChar - "'")* "'" +impl<'s> Parser<'s, PubidLiteral<'s>> for PubidLiteral<'s> { + fn parse(input: &'s str) -> IResult<&str, PubidLiteral<'s>> { + alt(( + map( + delimited(char('"'), recognize(many0(PubidChar::parse)), char('"')), + |pubid_literal| PubidLiteral::DoubleQuoted(pubid_literal), + ), + map( + delimited( + char('\''), + recognize(many0(recognize(not(char('\''))).and_then(PubidChar::parse))), + char('\''), + ), + |pubid_literal| PubidLiteral::SingleQuoted(pubid_literal), + ), + ))(input) + } +} + +/// [13] PubidChar ::= #x20 | #xD | #xA | [a-zA-Z0-9] | [-'()+,./:=?;!*#@$_%] +impl Parser<'_, PubidChar> for PubidChar { + fn parse(input: &'_ str) -> IResult<&str, PubidChar> { + map( + satisfy( + |c| matches!(c, '\u{20}' | '\u{D}' | '\u{A}' | 'a'..='z' | 'A'..='Z' | '0'..='9'), + ), + |pubid_char| PubidChar(pubid_char), + )(input) + } +} + +/// [14] CharData ::= [^<&]* - ([^<&]* ']]>' [^<&]*) +impl<'s> Parser<'s, CharData<'s>> for CharData<'s> { + fn parse(input: &'s str) -> IResult<&str, CharData<'s>> { + map( + recognize(many_till( + none_of("<&"), + peek(alt((recognize(one_of("<&")), tag("]]>")))), + )), + |char_data| CharData(char_data), + )(input) + } +} + +/// Comment ::= '' +impl<'s> Parser<'s, Comment<'s>> for Comment<'s> { + fn parse(input: &'s str) -> IResult<&str, Comment<'s>> { + map( + delimited( + tag(""), + ), + |comment| Comment(comment), + )(input) + } +} + +/// [16] PI ::= '' Char*)))? '?>' +impl<'s> Parser<'s, PI<'s>> for PI<'s> { + fn parse(input: &'s str) -> IResult<&str, PI<'s>> { + map( + delimited( + tag(""))), + ))), + ), + tag("?>"), + ), + |(target, instruction)| PI { + target, + instruction, + }, + )(input) + } +} + +/// [17] PITarget ::= Name - (('X' | 'x') ('M' | 'm') ('L' | 'l')) +impl<'s> Parser<'s, PITarget<'s>> for PITarget<'s> { + fn parse(input: &'s str) -> IResult<&str, PITarget<'s>> { + let (rest, name) = Name::parse(input)?; + if name.0.to_lowercase() == "xml" { + return Err(Err::Error(Error { + input, + // TODO: check if better error to return + code: ErrorKind::Tag, + })); + } else { + return Ok((rest, PITarget(name))); + } + } +} + +/// [18] CDSect ::= CDStart CData CDEnd +impl<'s> Parser<'s, CDSect<'s>> for CDSect<'s> { + fn parse(input: &'s str) -> IResult<&str, CDSect<'s>> { + map( + delimited(CDStart::parse, CData::parse, CDEnd::parse), + |c_data| CDSect(c_data), + )(input) + } +} + +/// [19] CDStart ::= ' for CDStart { + fn parse(input: &'_ str) -> IResult<&str, CDStart> { + value(CDStart, tag("' Char*)) +impl<'s> Parser<'s, CData<'s>> for CData<'s> { + fn parse(input: &'s str) -> IResult<&str, CData<'s>> { + map( + recognize(many_till(Char::parse, peek(tag("]]>")))), + |c_data| CData(c_data), + )(input) + } +} + +/// [21] CDEnd ::= ']]>' +impl Parser<'_, CDEnd> for CDEnd { + fn parse(input: &'_ str) -> IResult<&str, CDEnd> { + value(CDEnd, tag("]]>"))(input) + } +} + +/// [22] prolog ::= XMLDecl? Misc* (doctypedecl Misc*)? +impl<'s> Parser<'s, Prolog<'s>> for Prolog<'s> { + fn parse(input: &'s str) -> IResult<&str, Prolog<'s>> { + tuple(( + opt(XMLDecl::parse), + many0(Misc::parse), + opt(tuple((DoctypeDecl::parse, many0(Misc::parse)))), + ))(input) + } +} + +/// [23] XMLDecl ::= '' +impl<'s> Parser<'s, XMLDecl<'s>> for XMLDecl<'s> { + fn parse(input: &'s str) -> IResult<&str, XMLDecl<'s>> { + map( + delimited( + tag("")), + ), + |(version_info, encoding_decl, sd_decl)| XMLDecl { + version_info, + encoding_decl, + sd_decl, + }, + )(input) + } +} + +/// [24] VersionInfo ::= S 'version' Eq ("'" VersionNum "'" | '"' VersionNum '"') +impl Parser<'_, VersionInfo> for VersionInfo { + fn parse(input: &'_ str) -> IResult<&str, VersionInfo> { + preceded( + tuple((S::parse, tag("version"), Eq::parse)), + alt(( + map( + delimited(char('\''), VersionNum::parse, char('\'')), + |version_info| VersionInfo::SingleQuoted(version_info), + ), + map( + delimited(char('"'), VersionNum::parse, char('"')), + |version_info| VersionInfo::DoubleQuoted(version_info), + ), + )), + )(input) + } +} + +/// [25] Eq ::= S? '=' S? +impl Parser<'_, Eq> for Eq { + fn parse(input: &'_ str) -> IResult<&str, Eq> { + value( + Eq, + recognize(tuple((opt(S::parse), char('='), opt(S::parse)))), + )(input) + } +} + +/// [26] VersionNum ::= '1.' [0-9]+ +impl Parser<'_, VersionNum> for VersionNum { + fn parse(input: &'_ str) -> IResult<&str, VersionNum> { + preceded( + tag("1."), + alt(( + value(VersionNum::One, char('0')), + value(VersionNum::OneDotOne, char('1')), + )), + )(input) + } +} + +/// [27] Misc ::= Comment | PI | S +impl<'s> Parser<'s, Misc<'s>> for Misc<'s> { + fn parse(input: &'s str) -> IResult<&str, Misc<'s>> { + alt(( + map(Comment::parse, |comment| Misc::Comment(comment)), + map(PI::parse, |pi| Misc::PI(pi)), + value(Misc::S, S::parse), + ))(input) + } +} + +/// [16] doctypedecl ::= '' +/// [28] doctypedecl ::= '' +impl<'s> Parser<'s, DoctypeDecl<'s>> for DoctypeDecl<'s> { + fn parse(input: &'s str) -> IResult<&str, DoctypeDecl<'s>> { + map( + delimited( + pair(tag(""), + ), + |(name, external_id, int_subset)| DoctypeDecl { + name, + external_id, + int_subset, + }, + )(input) + } +} + +/// [28a] DeclSep ::= PEReference | S +impl<'s> Parser<'s, DeclSep<'s>> for DeclSep<'s> { + fn parse(input: &'s str) -> IResult<&str, DeclSep<'s>> { + alt(( + map(PEReference::parse, |pe_reference| { + DeclSep::PEReference(pe_reference) + }), + value(DeclSep::S, S::parse), + ))(input) + } +} + +/// [28b] intSubset ::= (markupdecl | DeclSep)* +impl<'s> Parser<'s, IntSubset<'s>> for IntSubset<'s> { + fn parse(input: &'s str) -> IResult<&str, IntSubset<'s>> { + many0(alt(( + map(MarkupDecl::parse, |markup_decl| { + IntSubsetDeclaration::MarkupDecl(markup_decl) + }), + map(DeclSep::parse, |decl_sep| { + IntSubsetDeclaration::DeclSep(decl_sep) + }), + )))(input) + } +} + +/// [29] markupdecl ::= elementdecl | AttlistDecl | EntityDecl | NotationDecl | PI | Comment +impl<'s> Parser<'s, MarkupDecl<'s>> for MarkupDecl<'s> { + fn parse(input: &'s str) -> IResult<&str, MarkupDecl<'s>> { + alt(( + map(Elementdecl::parse, |elementdecl| { + MarkupDecl::Elementdecl(elementdecl) + }), + map(AttlistDecl::parse, |attlist_decl| { + MarkupDecl::AttlistDecl(attlist_decl) + }), + map(EntityDecl::parse, |entity_decl| { + MarkupDecl::EntityDecl(entity_decl) + }), + map(NotationDecl::parse, |notation_decl| { + MarkupDecl::NotationDecl(notation_decl) + }), + map(PI::parse, |pi| MarkupDecl::PI(pi)), + map(Comment::parse, |comment| MarkupDecl::Comment(comment)), + ))(input) + } +} + +/// [30] extSubset ::= TextDecl? extSubsetDecl +impl<'s> Parser<'s, ExtSubset<'s>> for ExtSubset<'s> { + fn parse(input: &'s str) -> IResult<&str, ExtSubset<'s>> { + map( + pair(opt(TextDecl::parse), ExtSubsetDecl::parse), + |(text_decl, ext_subset_decl)| ExtSubset { + text_decl, + ext_subset_decl, + }, + )(input) + } +} + +/// [31] extSubsetDecl ::= ( markupdecl | conditionalSect | DeclSep)* +impl<'s> Parser<'s, ExtSubsetDecl<'s>> for ExtSubsetDecl<'s> { + fn parse(input: &'s str) -> IResult<&str, ExtSubsetDecl<'s>> { + many0(alt(( + map(MarkupDecl::parse, |markup_decl| { + ExtSubsetDeclaration::MarkupDecl(markup_decl) + }), + map(ConditionalSect::parse, |conditional_sect| { + ExtSubsetDeclaration::ConditionalSect(conditional_sect) + }), + map(DeclSep::parse, |decl_sep| { + ExtSubsetDeclaration::DeclSep(decl_sep) + }), + )))(input) + } +} + +/// [32] SDDecl ::= S 'standalone' Eq (("'" ('yes' | 'no') "'") | ('"' ('yes' | 'no') '"')) +impl Parser<'_, SDDecl> for SDDecl { + fn parse(input: &'_ str) -> IResult<&str, SDDecl> { + preceded( + tuple((S::parse, tag("standalone"), Eq::parse)), + alt(( + delimited( + char('\''), + alt(( + value(SDDecl::SingleQuoted(true), tag("yes")), + value(SDDecl::SingleQuoted(false), tag("no")), + )), + char('\''), + ), + delimited( + char('"'), + alt(( + value(SDDecl::DoubleQuoted(true), tag("yes")), + value(SDDecl::DoubleQuoted(false), tag("no")), + )), + char('"'), + ), + )), + )(input) + } +} + +// (Productions 33 through 38 have been removed.) + +/// [39] element ::= EmptyElemTag | STag content ETag +impl<'s> Parser<'s, Element<'s>> for Element<'s> { + fn parse(input: &'s str) -> IResult<&str, Element<'s>> { + alt(( + map(EmptyElemTag::parse, |empty_elem_tag| { + Element::Empty(empty_elem_tag) + }), + map( + tuple((STag::parse, Content::parse, ETag::parse)), + |(s_tag, content, e_tag)| Element::NotEmpty(s_tag, content, e_tag), + ), + ))(input) + } +} + +/// [12] STag ::= '<' QName (S Attribute)* S? '>' +/// [40] STag ::= '<' Name (S Attribute)* S? '>' +impl<'s> Parser<'s, STag<'s>> for STag<'s> { + fn parse(input: &'s str) -> IResult<&str, STag<'s>> { + map( + delimited( + tag("<"), + pair(QName::parse, many0(preceded(S::parse, Attribute::parse))), + pair(opt(S::parse), tag(">")), + ), + |(name, attributes)| STag { name, attributes }, + )(input) + } +} + +/// [15] Attribute ::= NSAttName Eq AttValue | QName Eq AttValue +impl<'s> Parser<'s, Attribute<'s>> for Attribute<'s> { + fn parse(input: &'s str) -> IResult<&str, Attribute<'s>> { + alt(( + map( + separated_pair(NSAttName::parse, Eq::parse, AttValue::parse), + |(ns_name, value)| Attribute::NamespaceDeclaration { ns_name, value }, + ), + map( + separated_pair(QName::parse, Eq::parse, AttValue::parse), + |(name, value)| Attribute::Attribute { name, value }, + ), + ))(input) + } +} +// pub type Attribute<'s> = (Name<'s>, AttValue<'s>); +/// [41] Attribute ::= Name Eq AttValue +// pub fn attribute(input: &str) -> IResult<&str, Attribute> { +// separated_pair(name, eq, att_value)(input) +// } + +/// [13] ETag ::= '' +/// [42] ETag ::= '' +impl<'s> Parser<'s, ETag<'s>> for ETag<'s> { + fn parse(input: &'s str) -> IResult<&str, ETag<'s>> { + map( + delimited(tag(""))), + |name| ETag { name }, + )(input) + } +} + +impl<'s> Parser<'s, ContentItem<'s>> for ContentItem<'s> { + fn parse(input: &'s str) -> IResult<&str, ContentItem<'s>> { + alt(( + map(Element::parse, |element| ContentItem::Element(element)), + map(Reference::parse, |reference| { + ContentItem::Reference(reference) + }), + map(CDSect::parse, |cd_sect| ContentItem::CDSect(cd_sect)), + map(PI::parse, |pi| ContentItem::PI(pi)), + map(Comment::parse, |comment| ContentItem::Comment(comment)), + ))(input) + } +} + +/// [43] content ::= CharData? ((element | Reference | CDSect | PI | Comment) CharData?)* +impl<'s> Parser<'s, Content<'s>> for Content<'s> { + fn parse(input: &'s str) -> IResult<&str, Content<'s>> { + map( + pair( + opt(CharData::parse), + many0(pair( + alt(( + map(Element::parse, |element| ContentItem::Element(element)), + map(Reference::parse, |reference| { + ContentItem::Reference(reference) + }), + map(CDSect::parse, |cd_sect| ContentItem::CDSect(cd_sect)), + map(PI::parse, |pi| ContentItem::PI(pi)), + map(Comment::parse, |comment| ContentItem::Comment(comment)), + )), + opt(CharData::parse), + )), + ), + |(char_data, content)| Content { char_data, content }, + )(input) + } +} + +/// [14] EmptyElemTag ::= '<' QName (S Attribute)* S? '/>' +/// [44] EmptyElemTag ::= '<' Name (S Attribute)* S? '/>' [WFC: Unique Att Spec] +impl<'s> Parser<'s, EmptyElemTag<'s>> for EmptyElemTag<'s> { + fn parse(input: &'s str) -> IResult<&str, EmptyElemTag<'s>> { + map( + delimited( + tag("<"), + pair(QName::parse, many0(preceded(S::parse, Attribute::parse))), + pair(opt(S::parse), tag("/>")), + ), + |(name, attributes)| EmptyElemTag { name, attributes }, + )(input) + } +} + +/// [17] elementdecl ::= '' +/// [45] elementdecl ::= '' +impl<'s> Parser<'s, Elementdecl<'s>> for Elementdecl<'s> { + fn parse(input: &'s str) -> IResult<&str, Elementdecl> { + map( + delimited( + pair(tag("")), + ), + |(name, contentspec)| Elementdecl { name, contentspec }, + )(input) + } +} + +/// [46] contentspec ::= 'EMPTY' | 'ANY' | Mixed | children +impl<'s> Parser<'s, Contentspec<'s>> for Contentspec<'s> { + fn parse(input: &'s str) -> IResult<&str, Contentspec<'s>> { + alt(( + value(Contentspec::Empty, tag("EMPTY")), + value(Contentspec::Any, tag("ANY")), + map(Mixed::parse, |mixed| Contentspec::Mixed(mixed)), + map(Children::parse, |children| Contentspec::Children(children)), + ))(input) + } +} + +/// Occurence ::= ('?' | '*' | '+')? +impl Parser<'_, Occurence> for Occurence { + fn parse(input: &'_ str) -> IResult<&str, Occurence> { + map( + opt(alt((tag("?"), tag("*"), tag("+")))), + |occurence| match occurence { + Some("?") => Occurence::Optional, + Some("*") => Occurence::Many0, + Some("+") => Occurence::Many1, + _ => Occurence::Once, + }, + )(input) + } +} + +/// [47] children ::= (choice | seq) ('?' | '*' | '+')? +impl<'s> Parser<'s, Children<'s>> for Children<'s> { + fn parse(input: &'s str) -> IResult<&str, Children<'s>> { + map( + pair( + alt(( + map(Choice::parse, |choice| ChildrenKind::Choice(choice)), + map(Seq::parse, |seq| ChildrenKind::Seq(seq)), + )), + Occurence::parse, + ), + |(kind, occurence)| Children { kind, occurence }, + )(input) + } +} + +/// [18] cp ::= (QName | choice | seq) ('?' | '*' | '+')? +/// [48] cp ::= (Name | choice | seq) ('?' | '*' | '+')? +impl<'s> Parser<'s, Cp<'s>> for Cp<'s> { + fn parse(input: &'s str) -> IResult<&str, Cp<'s>> { + map( + pair( + alt(( + map(QName::parse, |name| CpKind::Name(name)), + map(Choice::parse, |choice| CpKind::Choice(choice)), + map(Seq::parse, |seq| CpKind::Seq(seq)), + )), + Occurence::parse, + ), + |(kind, occurence)| Cp { kind, occurence }, + )(input) + } +} + +/// [49] choice ::= '(' S? cp ( S? '|' S? cp )+ S? ')' +impl<'s> Parser<'s, Choice<'s>> for Choice<'s> { + fn parse(input: &'s str) -> IResult<&str, Choice<'s>> { + map( + delimited( + pair(tag("("), opt(S::parse)), + pair( + Cp::parse, + many1(preceded( + tuple((opt(S::parse), tag("|"), opt(S::parse))), + Cp::parse, + )), + ), + pair(opt(S::parse), tag(")")), + ), + |(head, tail)| { + let choice = vec![vec![head], tail].concat(); + Choice(choice) + }, + )(input) + } +} + +/// [50] seq ::= '(' S? cp ( S? ',' S? cp )* S? ')' +impl<'s> Parser<'s, Seq<'s>> for Seq<'s> { + fn parse(input: &'s str) -> IResult<&str, Seq<'s>> { + map( + delimited( + pair(tag("("), opt(S::parse)), + pair( + Cp::parse, + many0(preceded( + tuple((opt(S::parse), tag(","), opt(S::parse))), + Cp::parse, + )), + ), + pair(opt(S::parse), tag(")")), + ), + |(head, tail)| { + let seq = vec![vec![head], tail].concat(); + Seq(seq) + }, + )(input) + } +} + +/// [19] Mixed ::= '(' S? '#PCDATA' (S? '|' S? QName)* S? ')*' | '(' S? '#PCDATA' S? ')' +/// [51] Mixed ::= '(' S? '#PCDATA' (S? '|' S? Name)* S? ')*' | '(' S? '#PCDATA' S? ')' +impl<'s> Parser<'s, Mixed<'s>> for Mixed<'s> { + fn parse(input: &'s str) -> IResult<&str, Mixed<'s>> { + alt(( + map( + delimited( + tuple((tag("("), S::parse, tag("#PCDATA"))), + many0(preceded( + tuple((opt(S::parse), tag("|"), opt(S::parse))), + QName::parse, + )), + pair(opt(S::parse), tag(")*")), + ), + |names| Mixed(names), + ), + value( + Mixed(Vec::new()), + tuple(( + tag("("), + opt(S::parse), + tag("#PCDATA"), + opt(S::parse), + tag(")"), + )), + ), + ))(input) + } +} + +/// [20] AttlistDecl ::= '' +/// [52] AttlistDecl ::= '' +impl<'s> Parser<'s, AttlistDecl<'s>> for AttlistDecl<'s> { + fn parse(input: &'s str) -> IResult<&str, AttlistDecl<'s>> { + map( + delimited( + pair(tag("")), + ), + |(element_type, att_defs)| AttlistDecl { + element_type, + att_defs, + }, + )(input) + } +} + +/// [21] AttDef ::= S (QName | NSAttName) S AttType S DefaultDecl +/// [53] AttDef ::= S Name S AttType S DefaultDecl +impl<'s> Parser<'s, AttDef<'s>> for AttDef<'s> { + fn parse(input: &'s str) -> IResult<&str, AttDef<'s>> { + map( + tuple(( + preceded( + S::parse, + alt(( + map(QName::parse, |q_name| AttDefName::QName(q_name)), + map(NSAttName::parse, |ns_att_name| { + AttDefName::NSAttName(ns_att_name) + }), + )), + ), + preceded(S::parse, AttType::parse), + preceded(S::parse, DefaultDecl::parse), + )), + |(name, att_type, default_decl)| AttDef { + name, + att_type, + default_decl, + }, + )(input) + } +} + +/// [54] AttType ::= StringType | TokenizedType | EnumeratedType +impl<'s> Parser<'s, AttType<'s>> for AttType<'s> { + fn parse(input: &'s str) -> IResult<&str, AttType<'s>> { + alt(( + value(AttType::StringType, StringType::parse), + map(TokenizedType::parse, |tokenized_type| { + AttType::TokenizedType(tokenized_type) + }), + map(EnumeratedType::parse, |enumerated_type| { + AttType::EnumeratedType(enumerated_type) + }), + ))(input) + } +} + +/// [55] StringType ::= 'CDATA' +impl Parser<'_, StringType> for StringType { + fn parse(input: &'_ str) -> IResult<&str, StringType> { + value(StringType, tag("CDATA"))(input) + } +} + +/// [56] TokenizedType ::= 'ID' | 'IDREF' | 'IDREFS' | 'ENTITY' | 'ENTITIES' | 'NMTOKEN' | 'NMTOKENS' +impl Parser<'_, TokenizedType> for TokenizedType { + fn parse(input: &'_ str) -> IResult<&str, TokenizedType> { + alt(( + value(TokenizedType::ID, tag("ID")), + // TODO: check if this is required + // try idrefs first to avoid losing 'S' + value(TokenizedType::IDRefs, tag("IDREFS")), + value(TokenizedType::IDRef, tag("IDREF")), + value(TokenizedType::Entity, tag("ENTITY")), + value(TokenizedType::Entities, tag("ENTITIES")), + // same here + value(TokenizedType::NMTokens, tag("NMTOKENS")), + value(TokenizedType::NMToken, tag("NMTOKEN")), + ))(input) + } +} + +/// [57] EnumeratedType ::= NotationType | Enumeration +impl<'s> Parser<'s, EnumeratedType<'s>> for EnumeratedType<'s> { + fn parse(input: &'s str) -> IResult<&str, EnumeratedType<'s>> { + alt(( + map(NotationType::parse, |notation_type| { + EnumeratedType::NotationType(notation_type) + }), + map(Enumeration::parse, |enumeration| { + EnumeratedType::Enumeration(enumeration) + }), + ))(input) + } +} + +/// [58] NotationType ::= 'NOTATION' S '(' S? Name (S? '|' S? Name)* S? ')' +impl<'s> Parser<'s, NotationType<'s>> for NotationType<'s> { + fn parse(input: &'s str) -> IResult<&str, NotationType<'s>> { + map( + delimited( + tuple((tag("NOTATION"), S::parse, tag("("), opt(S::parse))), + pair( + Name::parse, + many0(preceded( + tuple((opt(S::parse), tag("|"), opt(S::parse))), + Name::parse, + )), + ), + pair(opt(S::parse), tag(")")), + ), + |(head, tail)| { + let notation_type = vec![vec![head], tail].concat(); + NotationType(notation_type) + }, + )(input) + } +} + +/// [59] Enumeration ::= '(' S? Nmtoken (S? '|' S? Nmtoken)* S? ')' +impl<'s> Parser<'s, Enumeration<'s>> for Enumeration<'s> { + fn parse(input: &'s str) -> IResult<&str, Enumeration<'s>> { + map( + delimited( + pair(tag("("), opt(S::parse)), + pair( + Nmtoken::parse, + many0(preceded( + tuple((opt(S::parse), tag("|"), opt(S::parse))), + Nmtoken::parse, + )), + ), + pair(opt(S::parse), tag(")")), + ), + |(head, tail)| { + let enumeration = vec![vec![head], tail].concat(); + Enumeration(enumeration) + }, + )(input) + } +} + +/// [60] DefaultDecl ::= '#REQUIRED' | '#IMPLIED' | (('#FIXED' S)? AttValue) +impl<'s> Parser<'s, DefaultDecl<'s>> for DefaultDecl<'s> { + fn parse(input: &'s str) -> IResult<&str, DefaultDecl<'s>> { + alt(( + value(DefaultDecl::Required, tag("#REQUIRED")), + value(DefaultDecl::Implied, tag("#IMPLIED")), + map( + pair(opt(pair(tag("#FIXED"), S::parse)), AttValue::parse), + |(must, att_value)| DefaultDecl::Fixed(must.is_some(), att_value), + ), + ))(input) + } +} + +/// [61] conditionalSect ::= includeSect | ignoreSect +impl<'s> Parser<'s, ConditionalSect<'s>> for ConditionalSect<'s> { + fn parse(input: &'s str) -> IResult<&str, ConditionalSect<'s>> { + alt(( + map(IncludeSect::parse, |include_sect| { + ConditionalSect::IncludeSect(include_sect) + }), + map(IgnoreSect::parse, |ignore_sect| { + ConditionalSect::IgnoreSect(ignore_sect) + }), + ))(input) + } +} + +/// [62] includeSect ::= '' +impl<'s> Parser<'s, IncludeSect<'s>> for IncludeSect<'s> { + fn parse(input: &'s str) -> IResult<&str, IncludeSect<'s>> { + map( + delimited( + tuple(( + tag(""), + ), + |ext_subset_decl| IncludeSect(ext_subset_decl), + )(input) + } +} + +/// [63] ignoreSect ::= '' +impl<'s> Parser<'s, IgnoreSect<'s>> for IgnoreSect<'s> { + fn parse(input: &'s str) -> IResult<&str, IgnoreSect<'s>> { + map( + delimited( + tuple(( + tag(""), + ), + |ignore_sect_contents| IgnoreSect(ignore_sect_contents), + )(input) + } +} + +/// [64] ignoreSectContents ::= Ignore ('' Ignore)* +impl<'s> Parser<'s, IgnoreSectContents<'s>> for IgnoreSectContents<'s> { + fn parse(input: &'s str) -> IResult<&str, IgnoreSectContents<'s>> { + map( + pair( + Ignore::parse, + many0(tuple(( + delimited(tag("")), + Ignore::parse, + ))), + ), + |(ignore, ignore_list)| IgnoreSectContents { + ignore, + ignore_list, + }, + )(input) + } +} + +/// [65] Ignore ::= Char* - (Char* ('') Char*) +impl<'s> Parser<'s, Ignore<'s>> for Ignore<'s> { + fn parse(input: &'s str) -> IResult<&str, Ignore<'s>> { + map( + recognize(many_till(Char::parse, peek(alt((tag("")))))), + |ignore| Ignore(ignore), + )(input) + } +} + +/// [66] CharRef ::= '&#' [0-9]+ ';' | '&#x' [0-9a-fA-F]+ ';' +impl<'s> Parser<'s, CharRef<'s>> for CharRef<'s> { + fn parse(input: &'s str) -> IResult<&str, CharRef<'s>> { + alt(( + delimited( + tag("&#"), + map(take_while(|c| matches!(c, '0'..='9')), |decimal| { + CharRef::Decimal(decimal) + }), + tag(";"), + ), + delimited( + tag("&#x"), + map( + take_while(|c| matches!(c, '0'..='9' | 'a'..='f' | 'A'..='F' )), + |hexadecimal| CharRef::Hexadecimal(hexadecimal), + ), + tag(";"), + ), + ))(input) + } +} + +/// [67] Reference ::= EntityRef | CharRef +impl<'s> Parser<'s, Reference<'s>> for Reference<'s> { + fn parse(input: &'s str) -> IResult<&str, Reference<'s>> { + alt(( + map(EntityRef::parse, |entity_ref| { + Reference::EntityRef(entity_ref) + }), + map(CharRef::parse, |char_ref| Reference::CharRef(char_ref)), + ))(input) + } +} + +/// [68] EntityRef ::= '&' Name ';' +impl<'s> Parser<'s, EntityRef<'s>> for EntityRef<'s> { + fn parse(input: &'s str) -> IResult<&str, EntityRef<'s>> { + map(delimited(tag("&"), Name::parse, tag(";")), |entity_ref| { + EntityRef(entity_ref) + })(input) + } +} + +/// [69] PEReference ::= '%' Name ';' +impl<'s> Parser<'s, PEReference<'s>> for PEReference<'s> { + fn parse(input: &'s str) -> IResult<&str, PEReference<'s>> { + map(delimited(tag("%"), Name::parse, tag(";")), |pe_reference| { + PEReference(pe_reference) + })(input) + } +} + +/// [70] EntityDecl ::= GEDecl | PEDecl +impl<'s> Parser<'s, EntityDecl<'s>> for EntityDecl<'s> { + fn parse(input: &'s str) -> IResult<&str, EntityDecl<'s>> { + alt(( + map(GEDecl::parse, |ge_decl| EntityDecl::GEDecl(ge_decl)), + map(PEDecl::parse, |pe_decl| EntityDecl::PEDecl(pe_decl)), + ))(input) + } +} + +/// [71] GEDecl ::= '' +impl<'s> Parser<'s, GEDecl<'s>> for GEDecl<'s> { + fn parse(input: &'s str) -> IResult<&str, GEDecl<'s>> { + map( + delimited( + pair(tag("")), + ), + |(name, entity_def)| GEDecl { name, entity_def }, + )(input) + } +} + +/// [72] PEDecl ::= '' +impl<'s> Parser<'s, PEDecl<'s>> for PEDecl<'s> { + fn parse(input: &'s str) -> IResult<&str, PEDecl<'s>> { + map( + delimited( + tuple((tag("")), + ), + |(name, pe_def)| PEDecl { name, pe_def }, + )(input) + } +} + +/// [73] EntityDef ::= EntityValue | (ExternalID NDataDecl?) +impl<'s> Parser<'s, EntityDef<'s>> for EntityDef<'s> { + fn parse(input: &'s str) -> IResult<&str, EntityDef<'s>> { + alt(( + map(EntityValue::parse, |entity_value| { + EntityDef::EntityValue(entity_value) + }), + map( + pair(ExternalID::parse, opt(NDataDecl::parse)), + |(external_id, n_data_decl)| EntityDef::ExternalID { + external_id, + n_data_decl, + }, + ), + ))(input) + } +} + +/// [74] PEDef ::= EntityValue | ExternalID +impl<'s> Parser<'s, PEDef<'s>> for PEDef<'s> { + fn parse(input: &'s str) -> IResult<&str, PEDef<'s>> { + alt(( + map(EntityValue::parse, |entity_value| { + PEDef::EntityValue(entity_value) + }), + map(ExternalID::parse, |external_id| { + PEDef::ExternalID(external_id) + }), + ))(input) + } +} + +/// [75] ExternalID ::= 'SYSTEM' S SystemLiteral | 'PUBLIC' S PubidLiteral S SystemLiteral +// pub fn external_id(input: &str) -> IResult<&str, ExternalID> { +impl<'s> Parser<'s, ExternalID<'s>> for ExternalID<'s> { + fn parse(input: &'s str) -> IResult<&str, ExternalID<'s>> { + alt(( + map( + preceded(pair(tag("SYSTEM"), S::parse), SystemLiteral::parse), + |system_identifier| ExternalID::SYSTEM { system_identifier }, + ), + map( + preceded( + pair(tag("PUBLIC"), S::parse), + separated_pair(PubidLiteral::parse, S::parse, SystemLiteral::parse), + ), + |(public_identifier, system_identifier)| ExternalID::PUBLIC { + public_identifier, + system_identifier, + }, + ), + ))(input) + } +} + +/// [76] NDataDecl ::= S 'NDATA' S Name +impl<'s> Parser<'s, NDataDecl<'s>> for NDataDecl<'s> { + fn parse(input: &'s str) -> IResult<&str, NDataDecl<'s>> { + map( + preceded(tuple((S::parse, tag("NDATA"), S::parse)), Name::parse), + |n_data_decl| NDataDecl(n_data_decl), + )(input) + } +} + +/// [77] TextDecl ::= '' +impl<'s> Parser<'s, TextDecl<'s>> for TextDecl<'s> { + fn parse(input: &'s str) -> IResult<&str, TextDecl<'s>> { + map( + delimited( + tag(""), + ), + |(version_info, encoding_decl)| TextDecl { + version_info, + encoding_decl, + }, + )(input) + } +} + +/// [78] extParsedEnt ::= TextDecl? content +impl<'s> Parser<'s, ExtParsedEnt<'s>> for ExtParsedEnt<'s> { + fn parse(input: &'s str) -> IResult<&str, ExtParsedEnt<'s>> { + map( + pair(opt(TextDecl::parse), Content::parse), + |(text_decl, content)| ExtParsedEnt { text_decl, content }, + )(input) + } +} + +/// [80] EncodingDecl ::= S 'encoding' Eq ('"' EncName '"' | "'" EncName +impl<'s> Parser<'s, EncodingDecl<'s>> for EncodingDecl<'s> { + fn parse(input: &'s str) -> IResult<&str, EncodingDecl<'s>> { + map( + preceded( + tuple((S::parse, tag("encoding"), Eq::parse)), + alt(( + delimited(char('"'), EncName::parse, char('"')), + delimited(char('\''), EncName::parse, char('\'')), + )), + ), + |encoding_decl| EncodingDecl(encoding_decl), + )(input) + } +} + +/// [81] EncName ::= [A-Za-z] ([A-Za-z0-9._] | '-')* +impl<'s> Parser<'s, EncName<'s>> for EncName<'s> { + fn parse(input: &'s str) -> IResult<&str, EncName<'s>> { + map( + recognize(pair( + satisfy(|c| matches!(c, 'A'..='Z' | 'a'..='z' )), + many0(satisfy( + |c| matches!(c, 'A'..='Z' | 'a'..='z' | '0'..='9' | '.' | '_' | '-' ), + )), + )), + |enc_name| EncName(enc_name), + )(input) + } +} + +/// [82] NotationDecl ::= '' +impl<'s> Parser<'s, NotationDecl<'s>> for NotationDecl<'s> { + fn parse(input: &'s str) -> IResult<&str, NotationDecl<'s>> { + map( + delimited( + pair(tag("")), + ), + |(name, id)| NotationDecl { name, id }, + )(input) + } +} + +/// [83] PublicID ::= 'PUBLIC' S PubidLiteral +impl<'s> Parser<'s, PublicID<'s>> for PublicID<'s> { + fn parse(input: &'s str) -> IResult<&str, PublicID<'s>> { + map( + preceded(pair(tag("PUBLIC"), S::parse), PubidLiteral::parse), + |public_id| PublicID(public_id), + )(input) + } +} + +#[cfg(test)] +mod tests { + use std::num::NonZero; + + use super::*; + + #[test] + fn test_char_data() { + assert_eq!( + Ok(("&def]]>ghi", CharData("abc"))), + CharData::parse("abc&def]]>ghi") + ); + assert_eq!( + Ok(("]]>ghi", CharData("abcdef"))), + CharData::parse("abcdef]]>ghi") + ); + assert_eq!( + Ok(("&defghi", CharData("abc"))), + CharData::parse("abc&defghi") + ); + assert_eq!( + Ok(("]]>def&ghi", CharData("abc"))), + CharData::parse("abc]]>def&ghi") + ); + assert_eq!( + Ok(("&ghi", CharData("abc]>def"))), + CharData::parse("abc]>def&ghi") + ); + } + + #[test] + fn test_comment() { + assert_eq!(Ok(("", Comment(""))), Comment::parse("")); + assert_eq!(Ok(("", Comment("asdf"))), Comment::parse("")); + assert_eq!(Ok(("", Comment("as-df"))), Comment::parse("")); + } + + #[test] + fn test_pi_target() { + assert_eq!(Ok((" ", PITarget(Name("asdf")))), PITarget::parse("asdf ")); + assert_eq!( + Ok((" ", PITarget(Name("xmlasdf")))), + PITarget::parse("xmlasdf ") + ); + assert_eq!( + Err(Err::Error(Error { + input: "xml ", + code: ErrorKind::Tag + })), + PITarget::parse("xml ") + ); + assert_eq!( + Err(Err::Error(Error { + input: "xMl ", + code: ErrorKind::Tag + })), + PITarget::parse("xMl ") + ); + } + + #[test] + fn test_cd_sect() { + assert_eq!( + Ok(("", CDSect(CData("Hello, world!")))), + CDSect::parse("Hello, world!]]>") + ) + } + + #[test] + fn test_cd_start() { + assert_eq!(Ok(("asdf", CDStart)), CDStart::parse("asdf", CData("asdf"))), CData::parse("asdf]]>asdf")); + assert_eq!( + Ok(("]]>asdf", CData("asdf") + ); + assert_eq!( + Ok(("]]>asdf", CData("Hello, world!"))), + CData::parse("Hello, world!]]>asdf") + ) + } + + #[test] + fn test_cd_end() { + assert_eq!(Ok(("asdf", CDEnd)), CDEnd::parse("]]>asdf")) + } +}