improve reliability

This commit is contained in:
Robin Appelman 2024-07-20 16:44:17 +02:00
commit a64225eda6
4 changed files with 163 additions and 14 deletions

View file

@ -185,6 +185,12 @@ version = "0.5.6"
source = "registry+https://github.com/rust-lang/crates.io-index" source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0717cef1bc8b636c6e1c1bbdefc09e6322da8a9321966e8928ef80d20f7f770f" checksum = "0717cef1bc8b636c6e1c1bbdefc09e6322da8a9321966e8928ef80d20f7f770f"
[[package]]
name = "log"
version = "0.4.22"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a7a70ba024b9dc04c27ea2f0c0548feb474ec5c54bba33a7f72f873a39d07b24"
[[package]] [[package]]
name = "logging-extractor" name = "logging-extractor"
version = "0.1.0" version = "0.1.0"
@ -196,6 +202,8 @@ dependencies = [
"serde_json", "serde_json",
"test-case", "test-case",
"thiserror", "thiserror",
"tracing",
"tracing-subscriber",
"tree-sitter", "tree-sitter",
"tree-sitter-php", "tree-sitter-php",
"walkdir", "walkdir",
@ -207,6 +215,34 @@ version = "2.7.4"
source = "registry+https://github.com/rust-lang/crates.io-index" source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "78ca9ab1a0babb1e7d5695e3530886289c18cf2f87ec19a575a0abdce112e3a3" checksum = "78ca9ab1a0babb1e7d5695e3530886289c18cf2f87ec19a575a0abdce112e3a3"
[[package]]
name = "nu-ansi-term"
version = "0.46.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "77a8165726e8236064dbb45459242600304b42a5ea24ee2948e18e023bf7ba84"
dependencies = [
"overload",
"winapi",
]
[[package]]
name = "once_cell"
version = "1.19.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3fdb12b2476b595f9358c5161aa467c2438859caa136dec86c26fdd2efe17b92"
[[package]]
name = "overload"
version = "0.1.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b15813163c1d831bf4a13c3610c05c0d03b39feb07f7e09fa234dac9b15aaf39"
[[package]]
name = "pin-project-lite"
version = "0.2.14"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "bda66fc9667c18cb2758a2ac84d1167245054bcf85d5d1aaa6923f45801bdd02"
[[package]] [[package]]
name = "proc-macro2" name = "proc-macro2"
version = "1.0.86" version = "1.0.86"
@ -300,12 +336,27 @@ dependencies = [
"serde", "serde",
] ]
[[package]]
name = "sharded-slab"
version = "0.1.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f40ca3c46823713e0d4209592e8d6e826aa57e928f09752619fc696c499637f6"
dependencies = [
"lazy_static",
]
[[package]] [[package]]
name = "similar" name = "similar"
version = "2.5.0" version = "2.5.0"
source = "registry+https://github.com/rust-lang/crates.io-index" source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "fa42c91313f1d05da9b26f267f931cf178d4aba455b4c4622dd7355eb80c6640" checksum = "fa42c91313f1d05da9b26f267f931cf178d4aba455b4c4622dd7355eb80c6640"
[[package]]
name = "smallvec"
version = "1.13.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3c5e1a9a646d36c3599cd173a41282daf47c44583ad367b8e6837255952e5c67"
[[package]] [[package]]
name = "strsim" name = "strsim"
version = "0.11.1" version = "0.11.1"
@ -376,6 +427,73 @@ dependencies = [
"syn", "syn",
] ]
[[package]]
name = "thread_local"
version = "1.1.8"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8b9ef9bad013ada3808854ceac7b46812a6465ba368859a37e2100283d2d719c"
dependencies = [
"cfg-if",
"once_cell",
]
[[package]]
name = "tracing"
version = "0.1.40"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c3523ab5a71916ccf420eebdf5521fcef02141234bbc0b8a49f2fdc4544364ef"
dependencies = [
"pin-project-lite",
"tracing-attributes",
"tracing-core",
]
[[package]]
name = "tracing-attributes"
version = "0.1.27"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "34704c8d6ebcbc939824180af020566b01a7c01f80641264eba0999f6c2b6be7"
dependencies = [
"proc-macro2",
"quote",
"syn",
]
[[package]]
name = "tracing-core"
version = "0.1.32"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c06d3da6113f116aaee68e4d601191614c9053067f9ab7f6edbcb161237daa54"
dependencies = [
"once_cell",
"valuable",
]
[[package]]
name = "tracing-log"
version = "0.2.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ee855f1f400bd0e5c02d150ae5de3840039a3f54b025156404e34c23c03f47c3"
dependencies = [
"log",
"once_cell",
"tracing-core",
]
[[package]]
name = "tracing-subscriber"
version = "0.3.18"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ad0f048c97dbd9faa9b7df56362b8ebcaa52adb06b498c050d2f4e32f90a7a8b"
dependencies = [
"nu-ansi-term",
"sharded-slab",
"smallvec",
"thread_local",
"tracing-core",
"tracing-log",
]
[[package]] [[package]]
name = "tree-sitter" name = "tree-sitter"
version = "0.22.6" version = "0.22.6"
@ -408,6 +526,12 @@ version = "0.2.2"
source = "registry+https://github.com/rust-lang/crates.io-index" source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "06abde3611657adf66d383f00b093d7faecc7fa57071cce2578660c9f1010821" checksum = "06abde3611657adf66d383f00b093d7faecc7fa57071cce2578660c9f1010821"
[[package]]
name = "valuable"
version = "0.1.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "830b7e5d4d90034032940e4ace0d9a9a057e7a45cd94e6c007832e39edb82f6d"
[[package]] [[package]]
name = "walkdir" name = "walkdir"
version = "2.5.0" version = "2.5.0"
@ -418,6 +542,22 @@ dependencies = [
"winapi-util", "winapi-util",
] ]
[[package]]
name = "winapi"
version = "0.3.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5c839a674fcd7a98952e593242ea400abe93992746761e38641405d28b00f419"
dependencies = [
"winapi-i686-pc-windows-gnu",
"winapi-x86_64-pc-windows-gnu",
]
[[package]]
name = "winapi-i686-pc-windows-gnu"
version = "0.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ac3b87c63620426dd9b991e5ce0329eff545bccbbb34f3be09ff6fb6ab51b7b6"
[[package]] [[package]]
name = "winapi-util" name = "winapi-util"
version = "0.1.8" version = "0.1.8"
@ -427,6 +567,12 @@ dependencies = [
"windows-sys", "windows-sys",
] ]
[[package]]
name = "winapi-x86_64-pc-windows-gnu"
version = "0.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "712e227841d057c1ee1cd2fb22fa7e5a5461ae8e48fa2ca79ec42cfc1931183f"
[[package]] [[package]]
name = "windows-sys" name = "windows-sys"
version = "0.52.0" version = "0.52.0"

View file

@ -10,6 +10,8 @@ rust-version = "1.66.0"
name = "logging-extractor" name = "logging-extractor"
[dependencies] [dependencies]
tracing = "0.1.40"
tracing-subscriber = "0.3.18"
thiserror = "1.0.63" thiserror = "1.0.63"
clap = { version = "4.5.9", features = ["derive"] } clap = { version = "4.5.9", features = ["derive"] }
serde = { version = "1.0.204", features = ["derive"] } serde = { version = "1.0.204", features = ["derive"] }

View file

@ -5,8 +5,4 @@ use thiserror::Error;
pub enum Error { pub enum Error {
#[error("Failed to determine absolute root path ({}: {err:#}", path.display())] #[error("Failed to determine absolute root path ({}: {err:#}", path.display())]
RealPath { path: PathBuf, err: std::io::Error }, RealPath { path: PathBuf, err: std::io::Error },
#[error("Failed to open source file ({}: {err:#}", path.display())]
Open { path: PathBuf, err: std::io::Error },
#[error("Failed to read source file ({}: {err:#}", path.display())]
Read { path: PathBuf, err: std::io::Error },
} }

View file

@ -3,6 +3,7 @@ use crate::extractor::LogExtractor;
use serde::{Deserialize, Serialize}; use serde::{Deserialize, Serialize};
use std::fs::File; use std::fs::File;
use std::io::{Read, Write}; use std::io::{Read, Write};
use tracing::error;
use walkdir::WalkDir; use walkdir::WalkDir;
pub mod error; pub mod error;
@ -31,25 +32,29 @@ pub fn extract_dir<W: Write>(root: &str, mut output: W) -> Result<(), Error> {
for file in WalkDir::new(root).into_iter().flatten() { for file in WalkDir::new(root).into_iter().flatten() {
let path = file.path(); let path = file.path();
if let Some(path) = path.to_str() { if let Some(path) = path.to_str() {
if path.ends_with(".php") { if file.file_type().is_file() && path.ends_with(".php") {
code_buff.clear(); code_buff.clear();
let rel_path = &path[root.len()..]; let rel_path = &path[root.len()..];
let mut fh = File::open(path).map_err(|err| Error::Open { let mut fh = match File::open(path) {
path: path.into(), Ok(fh) => fh,
err, Err(err) => {
})?; error!(?err, path, "error opening file");
fh.read_to_string(&mut code_buff) continue;
.map_err(|err| Error::Read { }
path: path.into(), };
err, let res = fh.read_to_string(&mut code_buff);
})?; if let Err(err) = res {
error!(?err, path, "error reading file");
continue;
}
for log_item in extractor.extract(rel_path, &code_buff) { for log_item in extractor.extract(rel_path, &code_buff) {
if !first_line { if !first_line {
writeln!(&mut output, ",").ok(); writeln!(&mut output, ",").ok();
} }
first_line = false; first_line = false;
write!(&mut output, "\t").ok();
let _ = serde_json::to_writer(&mut output, &log_item); let _ = serde_json::to_writer(&mut output, &log_item);
} }
} }