Split out parts of noseyparker into additional internal crates

.gitignore

@@ -13,3 +13,6 @@
 
 # scripts/create-release.zsh output directory
 /release
+
+# Ignore generated credentials from google-github-actions/auth
+gha-creds-*.json

Cargo.toml

@@ -8,12 +8,15 @@ rust-version = "1.70"
 
 license = "Apache-2.0"
 authors = ["Brad Larsen <bradford.larsen@praetorian.com>"]
+
 homepage = "https://github.com/praetorian-inc/noseyparker"
 repository = "https://github.com/praetorian-inc/noseyparker"
+
 version = "0.16.0-dev"
 
 publish = false
 
+
 [profile.release]
 # Generate debug symbols even in release builds
 # Used for cargo-instruments: https://github.com/cmyr/cargo-instruments
@@ -22,6 +25,7 @@ publish = false
 lto = "thin"
 opt-level = 3  # default for release profile
 
+
 # Insta benefits from being compiled in release mode, even as dev dependency.
 [profile.dev.package.insta]
 opt-level = 3

crates/bstring-serde/Cargo.toml

@@ -0,0 +1,16 @@
+[package]
+name = "bstring-serde"
+edition.workspace = true
+rust-version.workspace = true
+license.workspace = true
+authors.workspace = true
+homepage.workspace = true
+repository.workspace = true
+version = "0.0.0"
+publish.workspace = true
+
+# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
+
+[dependencies]
+bstr = { version = "1.0", features = ["serde"] }
+serde = { version = "1.0", features = ["derive"] }

crates/content-guesser/Cargo.toml

@@ -8,7 +8,7 @@ homepage.workspace = true
 repository.workspace = true
 publish.workspace = true
 
-name = "content_guesser"
+name = "content-guesser"
 version = "0.0.0"
 
 [features]

crates/input-enumerator/Cargo.toml

@@ -0,0 +1,41 @@
+[package]
+name = "input-enumerator"
+edition.workspace = true
+rust-version.workspace = true
+license.workspace = true
+authors.workspace = true
+homepage.workspace = true
+repository.workspace = true
+version = "0.0.0"
+publish.workspace = true
+
+[features]
+gix_debug = ["gix-object/verbose-object-parsing-errors"]
+
+[dependencies]
+progress = { path = "../progress" }
+
+anyhow = { version = "1.0" }
+bstr = { version = "1.0", features = ["serde"] }
+bstring-serde = { path = "../bstring-serde" }
+fixedbitset = "0.4"
+
+# The following two dependencies get enabled by the `gix_debug` feature
+#
+# note that the `verbose-object-parsing-errors` feature is:
+# - broken in gix 0.53 + gix-object 0.36,
+# - broken in gix 0.52 + gix-object 0.35
+# - not broken in gix 0.51 + gix-object 0.33
+gix = { version = "0.55", features = ["max-performance", "serde"] }
+gix-object = { version = "0.38", features = ["verbose-object-parsing-errors"], optional = true }
+
+ignore = "0.4"
+petgraph = "0.6"
+roaring = "0.10"
+serde = { version = "1.0", features = ["derive"] }
+smallvec = { version = "1.11", features = ["const_generics", "const_new", "union"] }
+tracing = "0.1"
+
+[dev-dependencies]
+pretty_assertions = "1.3"
+proptest = "1.0"

crates/noseyparker/src/git_commit_metadata.rs → crates/input-enumerator/src/git_commit_metadata.rs

@@ -2,7 +2,7 @@ use bstr::BString;
 use gix::ObjectId;
 use gix::date::Time;
 
-use crate::utils::BStringSerde;
+use bstring_serde::BStringSerde;
 
 
 // FIXME: figure out how to do this without allocating

crates/noseyparker/src/git_metadata_graph.rs → crates/input-enumerator/src/git_metadata_graph.rs

@@ -13,7 +13,7 @@ use std::time::Instant;
 use tracing::{debug, warn};
 
 use crate::bstring_table::BStringTable;
-use crate::progress::Progress;
+use progress::Progress;
 
 type Symbol = crate::bstring_table::Symbol<u32>;
 

crates/noseyparker/src/input_enumerator/git_repo_enumerator.rs → crates/input-enumerator/src/git_repo_enumerator.rs

@@ -8,7 +8,8 @@ use tracing::{error_span, warn};
 use crate::blob_appearance::{BlobAppearance, BlobAppearanceSet};
 use crate::git_commit_metadata::CommitMetadata;
 use crate::git_metadata_graph::GitMetadataGraph;
-use crate::progress::Progress;
+
+use progress::Progress;
 
 // -------------------------------------------------------------------------------------------------
 // implementation helpers

crates/noseyparker/src/input_enumerator.rs → crates/input-enumerator/src/lib.rs

@@ -1,10 +1,15 @@
+pub mod blob_appearance;
+pub mod bstring_table;
+pub mod git_commit_metadata;
+pub mod git_metadata_graph;
+
 use anyhow::Result;
 use ignore::{DirEntry, WalkBuilder, WalkState};
 use std::path::{Path, PathBuf};
 use std::sync::Mutex;
 use tracing::{debug, error, warn};
 
-use crate::progress::Progress;
+use progress::Progress;
 
 mod git_repo_enumerator;
 pub use git_repo_enumerator::{GitRepoEnumerator, GitRepoWithMetadataEnumerator, GitRepoResult};