From 932161e5817561028bdb5685182ad3f78db5e1b5 Mon Sep 17 00:00:00 2001
From: Max Wipfli <mail@maxwipfli.ch>
Date: Fri, 4 Jun 2021 11:31:43 +0200
Subject: [PATCH] LibWeb: Be more forgiving when adding source positions in
 HTMLTokenizer

This patch changes HTMLTokenizer::nth_last_position to not fail if the
requested position is not available. Rather, it will just return (0-0).

While this is not the correct solution, it prevents the tokenizer from
crashing just because it cannot find a source position. This should only
affect SyntaxHighlighter.
---
 Userland/Libraries/LibWeb/HTML/Parser/HTMLToken.cpp   |  8 +++++---
 .../Libraries/LibWeb/HTML/Parser/HTMLTokenizer.cpp    | 11 ++++++++++-
 Userland/Libraries/LibWeb/HTML/Parser/HTMLTokenizer.h |  2 +-
 3 files changed, 16 insertions(+), 5 deletions(-)

diff --git a/Userland/Libraries/LibWeb/HTML/Parser/HTMLToken.cpp b/Userland/Libraries/LibWeb/HTML/Parser/HTMLToken.cpp
index fe2ae1f057..7a81844fd2 100644
--- a/Userland/Libraries/LibWeb/HTML/Parser/HTMLToken.cpp
+++ b/Userland/Libraries/LibWeb/HTML/Parser/HTMLToken.cpp
@@ -57,9 +57,11 @@ String HTMLToken::to_string() const
         builder.append("' }");
     }
 
-    builder.appendff("@{}:{}-{}:{}",
-        m_start_position.line, m_start_position.column,
-        m_end_position.line, m_end_position.column);
+    if (type() == HTMLToken::Type::Character) {
+        builder.appendff("@{}:{}", m_start_position.line, m_start_position.column);
+    } else {
+        builder.appendff("@{}:{}-{}:{}", m_start_position.line, m_start_position.column, m_end_position.line, m_end_position.column);
+    }
 
     return builder.to_string();
 }
diff --git a/Userland/Libraries/LibWeb/HTML/Parser/HTMLTokenizer.cpp b/Userland/Libraries/LibWeb/HTML/Parser/HTMLTokenizer.cpp
index 638ba37bea..7f9d17873c 100644
--- a/Userland/Libraries/LibWeb/HTML/Parser/HTMLTokenizer.cpp
+++ b/Userland/Libraries/LibWeb/HTML/Parser/HTMLTokenizer.cpp
@@ -207,6 +207,15 @@ Optional<u32> HTMLTokenizer::peek_code_point(size_t offset) const
     return *it;
 }
 
+HTMLToken::Position HTMLTokenizer::nth_last_position(size_t n)
+{
+    if (n + 1 > m_source_positions.size()) {
+        dbgln_if(TOKENIZER_TRACE_DEBUG, "(Tokenizer::nth_last_position) Invalid position requested: {}th-last of {}. Returning (0-0).", n, m_source_positions.size());
+        return HTMLToken::Position { 0, 0 };
+    };
+    return m_source_positions.at(m_source_positions.size() - 1 - n);
+}
+
 Optional<HTMLToken> HTMLTokenizer::next_token()
 {
     {
@@ -2639,7 +2648,7 @@ void HTMLTokenizer::will_emit(HTMLToken& token)
 {
     if (token.is_start_tag())
         m_last_emitted_start_tag = token;
-    token.m_end_position = m_source_positions.last();
+    token.m_end_position = nth_last_position(0);
 }
 
 bool HTMLTokenizer::current_end_tag_token_is_appropriate() const
diff --git a/Userland/Libraries/LibWeb/HTML/Parser/HTMLTokenizer.h b/Userland/Libraries/LibWeb/HTML/Parser/HTMLTokenizer.h
index 0024bcb08f..284b83e34b 100644
--- a/Userland/Libraries/LibWeb/HTML/Parser/HTMLTokenizer.h
+++ b/Userland/Libraries/LibWeb/HTML/Parser/HTMLTokenizer.h
@@ -147,7 +147,7 @@ private:
     bool consumed_as_part_of_an_attribute() const;
 
     void restore_to(const Utf8CodePointIterator& new_iterator);
-    auto& nth_last_position(size_t n = 0) { return m_source_positions.at(m_source_positions.size() - 1 - n); }
+    HTMLToken::Position nth_last_position(size_t n = 0);
 
     State m_state { State::Data };
     State m_return_state { State::Data };