What's the main reason ripgrep is fast?

According to the README, ripgrep is fast for several interconnected reasons [README.md:L183-L210]:

1. Rust's regex engine: It's built on top of Rust's regex engine, which uses finite automata, SIMD, and aggressive literal optimizations to make searching very fast. (PCRE2 support is also available via the -P/--pcre2 flag.)

2. Unicode support with performance: Rust's regex library maintains performance while providing full Unicode support by building UTF-8 decoding directly into its deterministic finite automaton engine.

3. Adaptive search strategy: It supports searching with either memory maps (better for single files) or incrementally with an intermediate buffer (better for large directories), and ripgrep automatically chooses the best strategy for you.

4. Efficient ignore pattern matching: It applies .gitignore patterns using a RegexSet, which allows a single file path to be matched against multiple glob patterns simultaneously.

5. Parallel directory traversal: It uses a lock-free parallel recursive directory iterator, courtesy of crossbeam and ignore crates.

The combination of these factors makes ripgrep significantly faster than comparable tools like The Silver Searcher, ack, and git grep.

FOLLOW_UPS:

• How does ripgrep handle .gitignore file parsing?
• What command-line flags disable ripgrep's automatic filtering?
• How does the ignore crate work in ripgrep?