First bit of inlines parsing

6 files changed, 148 insertions, 72 deletions

diff --git a/.vscode/launch.json b/.vscode/launch.json
new file mode 100644
index 0000000..acc54de
--- /dev/null
+++ b/.vscode/launch.json
@@ -0,0 +1,41 @@
+{
+    // Verwendet IntelliSense zum Ermitteln möglicher Attribute.
+    // Zeigen Sie auf vorhandene Attribute, um die zugehörigen Beschreibungen anzuzeigen.
+    // Weitere Informationen finden Sie unter https://go.microsoft.com/fwlink/?linkid=830387
+    "version": "0.2.0",
+    "configurations": [
+        {
+            "type": "lldb",
+            "request": "launch",
+            "name": "Debug executable on README",
+            "cargo": {
+                "args": [ "build", "--bin=rst", "--package=rst" ],
+                "filter": { "kind": "bin" }
+            },
+            "args": [ "README.rst" ],
+            "cwd": "${workspaceFolder}"
+        },
+        {
+            "type": "lldb",
+            "request": "launch",
+            "name": "Debug unit tests in lib",
+            "cargo": {
+                "args": [ "test", "--no-run", "--lib", "--package=rst" ],
+                "filter": { "kind": "lib" }
+            },
+            "args": [],
+            "cwd": "${workspaceFolder}"
+        },
+        {
+            "type": "lldb",
+            "request": "launch",
+            "name": "Debug unit tests in bin",
+            "cargo": {
+                "args": [ "test", "--no-run", "--bin=rst", "--package=rst" ],
+                "filter": { "kind": "bin" }
+            },
+            "args": [],
+            "cwd": "${workspaceFolder}"
+        }
+    ]
+}
\ No newline at end of file
diff --git a/Cargo.toml b/Cargo.toml
index 7f2f6c1..b5aa79e 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -24,7 +24,7 @@ path = 'src/bin.rs'
 failure = '0.1.3'
 failure_derive = '0.1.3'
 url = '1.7.2'
-regex = '1.0.6'
+regex = '1.1.0'
 bitflags = '1.0.4'
 unicode_categories = '0.1.1'
 pest        = { git = 'https://github.com/pest-parser/pest' }
diff --git a/src/parser/conversion.rs b/src/parser/conversion.rs
index def67e5..ad214d5 100644
--- a/src/parser/conversion.rs
+++ b/src/parser/conversion.rs
@@ -1,7 +1,7 @@
 mod block;
+mod inline;
 
 use failure::Error;
-use failure_derive::Fail;
 use pest::iterators::Pairs;
 
 use crate::document_tree::{
@@ -12,15 +12,6 @@ use crate::document_tree::{
 use super::pest_rst::Rule;
 
 
-#[derive(Debug, Fail)]
-enum ConversionError {
-    #[fail(display = "unknown rule: {:?}", rule)]
-    UnknownRuleError {
-        rule: Rule,
-    },
-}
-
-
 pub fn convert_document(pairs: Pairs<Rule>) -> Result<e::Document, Error> {
     let structural_elems = pairs.map(block::convert_ssubel)
         .filter_map(|elem| match elem { Ok(Some(e)) => Some(Ok(e)), Err(e) => Some(Err(e)), Ok(None) => None })
diff --git a/src/parser/conversion/block.rs b/src/parser/conversion/block.rs
index 0b638e7..5a92ed6 100644
--- a/src/parser/conversion/block.rs
+++ b/src/parser/conversion/block.rs
@@ -13,20 +13,20 @@ use crate::parser::{
     pest_rst::Rule,
     pair_ext_parse::PairExt,
 };
-use super::ConversionError;
+use super::inline::convert_inline;
 
 
 pub fn convert_ssubel(pair: Pair<Rule>) -> Result<Option<c::StructuralSubElement>, Error> {
     // TODO: This is just a proof of concep. Keep closely to DTD in final version!
     Ok(Some(match pair.as_rule() {
         Rule::title            => convert_title(pair).into(),
-        Rule::paragraph        => e::Paragraph::with_children(vec![pair.as_str().into()]).into(),
+        Rule::paragraph        => convert_paragraph(pair)?.into(),
         Rule::target           => convert_target(pair)?.into(),
         Rule::substitution_def => convert_substitution_def(pair)?.into(),
         Rule::admonition_gen   => convert_admonition_gen(pair)?.into(),
         Rule::image            => convert_image::<e::Image>(pair)?.into(),
         Rule::EOI              => return Ok(None),
-        rule => return Err(ConversionError::UnknownRuleError { rule }.into()),
+        rule => panic!("unknown rule {:?}", rule),
     }))
 }
 
@@ -47,6 +47,13 @@ fn convert_title(pair: Pair<Rule>) -> e::Title {
     ])
 }
 
+
+fn convert_paragraph(pair: Pair<Rule>) -> Result<e::Paragraph, Error> {
+    let children = pair.into_inner().map(convert_inline).collect::<Result<_,_>>()?;
+    Ok(e::Paragraph::with_children(children))
+}
+
+
 fn convert_target(pair: Pair<Rule>) -> Result<e::Target, Error> {
     let mut attrs = a::Target {
         anonymous: false,
diff --git a/src/parser/conversion/inline.rs b/src/parser/conversion/inline.rs
new file mode 100644
index 0000000..0b6f659
--- /dev/null
+++ b/src/parser/conversion/inline.rs
@@ -0,0 +1,38 @@
+use failure::Error;
+use pest::iterators::Pair;
+
+use crate::document_tree::{
+    ExtraAttributes,
+    elements as e,
+    element_categories as c,
+//    attribute_types::ID,
+    extra_attributes as a,
+};
+
+use crate::parser::{
+    pest_rst::Rule,
+//    pair_ext_parse::PairExt,
+};
+
+
+pub fn convert_inline(pair: Pair<Rule>) -> Result<c::TextOrInlineElement, Error> {
+    Ok(match pair.as_rule() {
+        Rule::str       => pair.as_str().into(),
+        Rule::reference => convert_reference(pair)?.into(),
+        rule => panic!("unknown rule {:?}", rule),
+    })
+}
+
+fn convert_reference(pair: Pair<Rule>) -> Result<e::Reference, Error> {
+    let name = None;
+    let uri = None;
+    let id = None;
+    let name_tokens = vec![];
+    let extra = a::Reference {
+        name: name,
+        refuri: uri,
+        refid: id,
+        refname: name_tokens,
+    };
+    Ok(e::Reference::with_extra(extra))
+}
diff --git a/src/rst.pest b/src/rst.pest
index e1e14ee..9d1bd54 100644
--- a/src/rst.pest
+++ b/src/rst.pest
@@ -63,7 +63,7 @@ bullet_item =  { bullet_marker ~ PUSH(" "+) ~ line ~ blank_line* ~ blist_body? ~
 blist_body  = _{ PEEK[..-1] ~ PUSH(" " ~ POP) ~ hanging_block ~ block* }
 
 // paragraph. A block type.
-paragraph =  { line ~ (PEEK[..] ~ line)* }
+paragraph =  { inlines }
 
 
 /* Directives: http://docutils.sourceforge.net/docs/ref/rst/restructuredtext.html#directives
@@ -89,9 +89,61 @@ admonition_gen     =  { ".." ~ PUSH(" "+) ~  admonition_type ~ "::" ~ (blank_lin
 admonition_type    =  { ^"attention" | ^"caution" | ^"danger" | ^"error" | ^"hint" | ^"important" | ^"note" | ^"tip" | ^"warning" }
 admonition_content = _{ PEEK[..-1] ~ PUSH("  " ~ POP) ~ hanging_block ~ block* } //TODO: merge with other directives?
 
-// TODO: use inlines here
-line       =  { !marker ~ !blank_line ~ (!NEWLINE ~ ANY)+ ~ NEWLINE }
-blank_line = _{ !marker ~ " "* ~ NEWLINE }
+
+
+/*
+ * inlines
+ */
+
+
+line       =  { !marker ~ inline+ ~ NEWLINE }
+blank_line = _{ !marker ~ !inline ~ " "* ~ NEWLINE }
+
+inlines = _{ !marker ~ inline+ ~ (NEWLINE ~ PEEK[..] ~ !marker ~ inline+ ~ NEWLINE)* }
+inline  = _{
+    reference
+    | str
+//     link ✓
+//     | str ✓
+//     | endline
+//     | ul_or_star_line
+//     | space
+//     | strong
+//     | emph
+//     | strike
+//     | note_reference
+//     | footnote
+//     //| citation
+//     | code
+//     | application_depent
+//     | entity
+//     | escaped_char
+//     | smart
+//     | symbol
+}
+
+str = { (!(NEWLINE | reference) ~ ANY)+ }
+
+// inline links
+reference = { reference_target | reference_explicit | reference_auto }
+
+reference_target = { reference_target_uq ~ "_" | reference_target_qu }
+reference_target_uq =  { (!("_"|":"|"`") ~ nonspacechar)* }
+reference_target_qu = _{ ( !("`"? ~ "`_") ~ "`" ~ !"``" ) ~ target_name_qu ~ ( "`" ~ !"``" ) ~ "_" }
+
+reference_explicit = { reference_label ~ "(" ~ " "* ~ reference_source ~ " "* ~ (NEWLINE ~ PEEK[..])? ~ reference_title ~ " "* ~ ")" }
+reference_label = { "[" ~ !"^" ~ (!"]" ~ inline)* ~ "]" }
+reference_source          =  { reference_source_contents }
+reference_source_contents = _{ ( (!("("|")"|">") ~ nonspacechar)+ | "(" ~ reference_source_contents ~ ")" )* }
+reference_title        = { ( reference_title_single | reference_title_double | "" ) }
+reference_title_single = { "'"  ~ ( !("'"  ~ " "+ ~ (")" | NEWLINE)) ~ ANY )* ~ "'" }
+reference_title_double = { "\"" ~ ( !("\"" ~ " "+ ~ (")" | NEWLINE)) ~ ANY )* ~ "\"" }
+
+reference_auto = { reference_embedded | reference_auto_url | reference_auto_email }
+reference_embedded = { "`" ~ reference_embedded_source ~ "<" ~ ASCII_ALPHA+ ~ "://" ~ (!(NEWLINE|">") ~ ANY)+ ~ ">`_" ~ "_"? }
+reference_embedded_source = { ( !("<"|":"|"`") ~ ( " " | nonspacechar | blank_line ) )* }
+reference_auto_url = { ASCII_ALPHA+ ~ "://" ~ (!(NEWLINE|">") ~ ANY)+ }
+reference_auto_email = { "<" ~ "mailto:"? ~ (ASCII_ALPHANUMERIC|"-"|"+"|"_"|"."|"/"|"!"|"%"|"~"|"$")+ ~ "@" ~ (!(NEWLINE | ">") ~ ANY)+ ~ ">" }
 
 
 /*
@@ -206,36 +258,12 @@ marker = _{ (bullet_marker | "..") ~ " " }
 //     optionally_indented_line
 // }
 
-// inlines = { ( !endline ~ inline | endline ~ &inline )+ ~ endline? }
 
-// inline = {
-//     link
-//     | str
-//     | endline
-//     | ul_or_star_line
-//     | space
-//     | strong
-//     | emph
-//     | strike
-//     | note_reference
-//     | footnote
-//     //| citation
-//     | code
-//     | application_depent
-//     | entity
-//     | escaped_char
-//     | smart
-//     | symbol
-// }
 
 // space = _{ spacechar+ }
 
 // str = { normal_char+ ~ str_chunk* }
-// str_chunk = _{ (normal_char | "_"+ ~ &alphanumeric)+ | apos_chunk }
-// apos_chunk = {
-//     // &{ extension(EXT_SMART) } ~
-//     "'" ~ &alphanumeric
-// }
+// str_chunk = _{ (normal_char | "_"+ ~ &alphanumeric)+ }
 
 // escaped_char = { "\\" ~ !NEWLINE ~ ("-" | "\\" | "`" | "|" | "*" | "_" | "{" | "}" | "[" | "]" | "(" | ")" | "#" | "+" | "." | "!" | ">" | "<") }
 
@@ -265,36 +293,7 @@ marker = _{ (bullet_marker | "..") ~ " " }
 //     "~~" ~ !whitespace ~ (!"~~" ~ inline)+ ~ "~~"
 // }
 
-// link = { reference_link | explicit_link | auto_link }
-
-// reference_link = { unquoted_ref_link_underbar | quoted_ref_link_underbar }
-// unquoted_ref_link_underbar = { unquoted_link_source ~ "_" }
-// quoted_ref_link_underbar = { ( !("`_" | "``_") ~ "`" ~ !"``" ) ~ target_name_qu ~ ( "`" ~ !"``" ) ~ "_" }
-
-// explicit_link = { label ~ "(" ~ sp ~ source ~ spnl ~ title ~ sp ~ ")" }
 
-// source = { source_contents }
-// source_contents = { ( (!("(" | ")" | ">") ~ nonspacechar)+ | "(" ~ source_contents ~ ")" )* }
-
-// title = { ( title_single | title_double | "" ) }
-// title_single = { "'" ~ ( !("'" ~ sp ~ (")" | NEWLINE)) ~ ANY )* ~ "'" }
-// title_double = { "\"" ~ ( !("\"" ~ sp ~ (")" | NEWLINE)) ~ ANY )* ~ "\"" }
-
-// auto_link = { embedded_link | auto_link_url | auto_link_email }
-// embedded_link = { "`" ~ embedded_ref_source ~ "<" ~ ASCII_ALPHA+ ~ "://" ~ (!(NEWLINE | ">") ~ ANY)+ ~ ">`_" ~ "_"? }
-// auto_link_url = { ASCII_ALPHA+ ~ "://" ~ (!(NEWLINE|">") ~ ANY)+ }
-// auto_link_email = { "<" ~ "mailto:"? ~ (ASCII_ALPHANUMERIC|"-"|"+"|"_"|"."|"/"|"!"|"%"|"~"|"$")+ ~ "@" ~ (!(NEWLINE | ">") ~ ANY)+ ~ ">" }
-
-// unquoted_link_source = { (!("_"|":"|"`") ~ nonspacechar)* }
-
-// embedded_ref_source = { ( !("<"|":"|"`") ~ ( " " | nonspacechar | blank_line ) )* }
-
-// label = {
-//     "[" ~ (
-//         !"^" //~ &{ extension(EXT_NOTES) }
-//         | &ANY //~ &{ extension(EXT_NOTES) }
-//     ) ~ (!"]" ~ inline)* ~ "]"
-// }
 
 
 // empty_title = { "" }