uutils/coreutils
0
0
Fork 0
mirror of https://github.com/uutils/coreutils.git synced 2026-06-10 15:48:22 -07:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #1672 from sylvestre/csplit2

Browse Source 
Implement csplit
This commit is contained in:
Sylvestre Ledru
2020-12-29 10:06:43 +01:00
committed by GitHub
parent da362ced71 bc4c82b132
commit 33987d896d
12 changed files with 3007 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Cargo.lock
Generated
+33 -10
View File
@@ -1,3 +1,5 @@
# This file is automatically @generated by Cargo.
# It is not intended for manual editing.
[[package]]
name = "advapi32-sys"
version = "0.2.0"
@@ -227,6 +229,7 @@ dependencies = [
"cc 1.0.61 (registry+https://github.com/rust-lang/crates.io-index)",
"conv 0.3.3 (registry+https://github.com/rust-lang/crates.io-index)",
"filetime 0.2.13 (registry+https://github.com/rust-lang/crates.io-index)",
"glob 0.3.0 (registry+https://github.com/rust-lang/crates.io-index)",
"lazy_static 1.4.0 (registry+https://github.com/rust-lang/crates.io-index)",
"libc 0.2.66 (registry+https://github.com/rust-lang/crates.io-index)",
"rand 0.7.3 (registry+https://github.com/rust-lang/crates.io-index)",
@@ -252,6 +255,7 @@ dependencies = [
"uu_cksum 0.0.1",
"uu_comm 0.0.1",
"uu_cp 0.0.1",
"uu_csplit 0.0.1",
"uu_cut 0.0.1",
"uu_date 0.0.1",
"uu_df 0.0.1",
@@ -495,7 +499,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"bstr 0.2.14 (registry+https://github.com/rust-lang/crates.io-index)",
"csv-core 0.1.10 (registry+https://github.com/rust-lang/crates.io-index)",
"itoa 0.4.6 (registry+https://github.com/rust-lang/crates.io-index)",
"itoa 0.4.7 (registry+https://github.com/rust-lang/crates.io-index)",
"ryu 1.0.5 (registry+https://github.com/rust-lang/crates.io-index)",
"serde 1.0.118 (registry+https://github.com/rust-lang/crates.io-index)",
]
@@ -622,6 +626,11 @@ dependencies = [
"wasi 0.9.0+wasi-snapshot-preview1 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "glob"
version = "0.2.11"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
name = "glob"
version = "0.3.0"
@@ -689,7 +698,7 @@ dependencies = [
[[package]]
name = "itoa"
version = "0.4.6"
version = "0.4.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
[[package]]
@@ -1150,7 +1159,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"proc-macro2 1.0.24 (registry+https://github.com/rust-lang/crates.io-index)",
"quote 1.0.8 (registry+https://github.com/rust-lang/crates.io-index)",
"syn 1.0.55 (registry+https://github.com/rust-lang/crates.io-index)",
"syn 1.0.56 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
@@ -1158,7 +1167,7 @@ name = "serde_json"
version = "1.0.60"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"itoa 0.4.6 (registry+https://github.com/rust-lang/crates.io-index)",
"itoa 0.4.7 (registry+https://github.com/rust-lang/crates.io-index)",
"ryu 1.0.5 (registry+https://github.com/rust-lang/crates.io-index)",
"serde 1.0.118 (registry+https://github.com/rust-lang/crates.io-index)",
]
@@ -1216,7 +1225,7 @@ dependencies = [
[[package]]
name = "syn"
version = "1.0.55"
version = "1.0.56"
source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"proc-macro2 1.0.24 (registry+https://github.com/rust-lang/crates.io-index)",
@@ -1490,6 +1499,19 @@ dependencies = [
"xattr 0.2.2 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
name = "uu_csplit"
version = "0.0.1"
dependencies = [
"failure 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)",
"failure_derive 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)",
"getopts 0.2.21 (registry+https://github.com/rust-lang/crates.io-index)",
"glob 0.2.11 (registry+https://github.com/rust-lang/crates.io-index)",
"regex 1.4.2 (registry+https://github.com/rust-lang/crates.io-index)",
"uucore 0.0.4",
"uucore_procs 0.0.4",
]
[[package]]
name = "uu_cut"
version = "0.0.1"
@@ -2355,7 +2377,7 @@ version = "0.0.4"
dependencies = [
"proc-macro2 1.0.24 (registry+https://github.com/rust-lang/crates.io-index)",
"quote 1.0.8 (registry+https://github.com/rust-lang/crates.io-index)",
"syn 1.0.55 (registry+https://github.com/rust-lang/crates.io-index)",
"syn 1.0.56 (registry+https://github.com/rust-lang/crates.io-index)",
]
[[package]]
@@ -2402,7 +2424,7 @@ dependencies = [
"log 0.4.11 (registry+https://github.com/rust-lang/crates.io-index)",
"proc-macro2 1.0.24 (registry+https://github.com/rust-lang/crates.io-index)",
"quote 1.0.8 (registry+https://github.com/rust-lang/crates.io-index)",
"syn 1.0.55 (registry+https://github.com/rust-lang/crates.io-index)",
"syn 1.0.56 (registry+https://github.com/rust-lang/crates.io-index)",
"wasm-bindgen-shared 0.2.69 (registry+https://github.com/rust-lang/crates.io-index)",
]
@@ -2422,7 +2444,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
dependencies = [
"proc-macro2 1.0.24 (registry+https://github.com/rust-lang/crates.io-index)",
"quote 1.0.8 (registry+https://github.com/rust-lang/crates.io-index)",
"syn 1.0.55 (registry+https://github.com/rust-lang/crates.io-index)",
"syn 1.0.56 (registry+https://github.com/rust-lang/crates.io-index)",
"wasm-bindgen-backend 0.2.69 (registry+https://github.com/rust-lang/crates.io-index)",
"wasm-bindgen-shared 0.2.69 (registry+https://github.com/rust-lang/crates.io-index)",
]
@@ -2556,6 +2578,7 @@ dependencies = [
"checksum generic-array 0.8.3 (registry+https://github.com/rust-lang/crates.io-index)" = "fceb69994e330afed50c93524be68c42fa898c2d9fd4ee8da03bd7363acd26f2"
"checksum getopts 0.2.21 (registry+https://github.com/rust-lang/crates.io-index)" = "14dbbfd5c71d70241ecf9e6f13737f7b5ce823821063188d7e46c41d371eebd5"
"checksum getrandom 0.1.15 (registry+https://github.com/rust-lang/crates.io-index)" = "fc587bc0ec293155d5bfa6b9891ec18a1e330c234f896ea47fbada4cadbe47e6"
"checksum glob 0.2.11 (registry+https://github.com/rust-lang/crates.io-index)" = "8be18de09a56b60ed0edf84bc9df007e30040691af7acd1c41874faac5895bfb"
"checksum glob 0.3.0 (registry+https://github.com/rust-lang/crates.io-index)" = "9b919933a397b79c37e33b77bb2aa3dc8eb6e165ad809e58ff75bc7db2e34574"
"checksum half 1.6.0 (registry+https://github.com/rust-lang/crates.io-index)" = "d36fab90f82edc3c747f9d438e06cf0a491055896f2a279638bb5beed6c40177"
"checksum hermit-abi 0.1.17 (registry+https://github.com/rust-lang/crates.io-index)" = "5aca5565f760fb5b220e499d72710ed156fdb74e631659e99377d9ebfbd13ae8"
@@ -2565,7 +2588,7 @@ dependencies = [
"checksum isatty 0.1.9 (registry+https://github.com/rust-lang/crates.io-index)" = "e31a8281fc93ec9693494da65fbf28c0c2aa60a2eaec25dc58e2f31952e95edc"
"checksum itertools 0.8.2 (registry+https://github.com/rust-lang/crates.io-index)" = "f56a2d0bc861f9165be4eb3442afd3c236d8a98afd426f65d92324ae1091a484"
"checksum itertools 0.9.0 (registry+https://github.com/rust-lang/crates.io-index)" = "284f18f85651fe11e8a991b2adb42cb078325c996ed026d994719efcfca1d54b"
"checksum itoa 0.4.6 (registry+https://github.com/rust-lang/crates.io-index)" = "dc6f3ad7b9d11a0c00842ff8de1b60ee58661048eb8049ed33c73594f359d7e6"
"checksum itoa 0.4.7 (registry+https://github.com/rust-lang/crates.io-index)" = "dd25036021b0de88a0aff6b850051563c6516d0bf53f8638938edbb9de732736"
"checksum js-sys 0.3.46 (registry+https://github.com/rust-lang/crates.io-index)" = "cf3d7383929f7c9c7c2d0fa596f325832df98c3704f2c60553080f7127a58175"
"checksum kernel32-sys 0.2.2 (registry+https://github.com/rust-lang/crates.io-index)" = "7507624b29483431c0ba2d82aece8ca6cdba9382bff4ddd0f7490560c056098d"
"checksum lazy_static 1.4.0 (registry+https://github.com/rust-lang/crates.io-index)" = "e2abad23fbc42b3700f2f279844dc832adb2b2eb069b2df918f455c4e18cc646"
@@ -2634,7 +2657,7 @@ dependencies = [
"checksum smallvec 0.6.13 (registry+https://github.com/rust-lang/crates.io-index)" = "f7b0758c52e15a8b5e3691eae6cc559f08eee9406e548a4477ba4e67770a82b6"
"checksum strsim 0.8.0 (registry+https://github.com/rust-lang/crates.io-index)" = "8ea5119cdb4c55b55d432abb513a0429384878c15dde60cc77b1c99de1a95a6a"
"checksum syn 0.11.11 (registry+https://github.com/rust-lang/crates.io-index)" = "d3b891b9015c88c576343b9b3e41c2c11a51c219ef067b264bd9c8aa9b441dad"
"checksum syn 1.0.55 (registry+https://github.com/rust-lang/crates.io-index)" = "a571a711dddd09019ccc628e1b17fe87c59b09d513c06c026877aa708334f37a"
"checksum syn 1.0.56 (registry+https://github.com/rust-lang/crates.io-index)" = "a9802ddde94170d186eeee5005b798d9c159fa970403f1be19976d0cfb939b72"
"checksum synom 0.11.3 (registry+https://github.com/rust-lang/crates.io-index)" = "a393066ed9010ebaed60b9eafa373d4b1baac186dd7e008555b0f702b51945b6"
"checksum synstructure 0.6.1 (registry+https://github.com/rust-lang/crates.io-index)" = "3a761d12e6d8dcb4dcf952a7a89b475e3a9d69e4a69307e01a470977642914bd"
"checksum tempfile 3.1.0 (registry+https://github.com/rust-lang/crates.io-index)" = "7a6e24d9338a0a5be79593e2fa15a648add6138caa803e2d5bc782c371732ca9"
Cargo.toml
+3
View File
@@ -37,6 +37,7 @@ feat_common_core = [
"cksum",
"comm",
"cp",
"csplit",
"cut",
"date",
"df",
@@ -241,6 +242,7 @@ chroot = { optional=true, version="0.0.1", package="uu_chroot", path="src/uu/c
cksum = { optional=true, version="0.0.1", package="uu_cksum", path="src/uu/cksum" }
comm = { optional=true, version="0.0.1", package="uu_comm", path="src/uu/comm" }
cp = { optional=true, version="0.0.1", package="uu_cp", path="src/uu/cp" }
csplit = { optional=true, version="0.0.1", package="uu_csplit", path="src/uu/csplit" }
cut = { optional=true, version="0.0.1", package="uu_cut", path="src/uu/cut" }
date = { optional=true, version="0.0.1", package="uu_date", path="src/uu/date" }
df = { optional=true, version="0.0.1", package="uu_df", path="src/uu/df" }
@@ -332,6 +334,7 @@ pin_winapi-util = { version="0.1.2, < 0.1.3", package="winapi-util" } ## winapi-
[dev-dependencies]
conv = "0.3"
filetime = "0.2"
glob = "0.3.0"
libc = "0.2"
rand = "0.7"
regex = "1.0"
GNUmakefile
+2
View File
@@ -53,6 +53,7 @@ PROGS := \
cksum \
comm \
cp \
csplit \
cut \
df \
dircolors \
@@ -160,6 +161,7 @@ TEST_PROGS := \
cksum \
comm \
cp \
csplit \
cut \
dircolors \
dirname \
README.md
+7 -6
View File
@@ -289,9 +289,9 @@ Utilities
| Done | Semi-Done | To Do |
|-----------|-----------|--------|
| arch | cp | chcon |
| base32 | expr | csplit |
| base64 | install | dd |
| basename | ls | numfmt |
| base32 | expr | dd |
| base64 | install | numfmt |
| basename | ls | stty |
| cat | more | pr |
| chgrp | od (`--strings` and 128-bit data types missing) | runcon |
| chmod | printf | stty |
@@ -299,9 +299,10 @@ Utilities
| chroot | split | |
| cksum | tail | |
| comm | test | |
| cut | date | |
| dircolors | join | |
| dirname | df | |
| csplit | date | |
| cut | join | |
| dircolors | df | |
| dirname | | |
| du | | |
| echo | | |
| env | | |
src/uu/csplit/Cargo.toml
+28
View File
@@ -0,0 +1,28 @@
[package]
name = "uu_csplit"
version = "0.0.1"
authors = ["uutils developers"]
license = "MIT"
description = "csplit ~ (uutils) Output pieces of FILE separated by PATTERN(s) to files 'xx00', 'xx01', ..., and output byte counts of each piece to standard output"
homepage = "https://github.com/uutils/coreutils"
repository = "https://github.com/uutils/coreutils/tree/master/src/uu/ls"
keywords = ["coreutils", "uutils", "cross-platform", "cli", "utility"]
categories = ["command-line-utilities"]
edition = "2018"
[lib]
path = "src/csplit.rs"
[dependencies]
getopts = "0.2.17"
failure = "0.1.1"
failure_derive = "0.1.1"
regex = "1.0.0"
glob = "0.2.11"
uucore = { version=">=0.0.4", package="uucore", path="../../uucore", features=["entries", "fs"] }
uucore_procs = { version=">=0.0.4", package="uucore_procs", path="../../uucore_procs" }
[[bin]]
name = "csplit"
path = "src/main.rs"
src/uu/csplit/src/csplit.rs
+761
View File
File diff suppressed because it is too large Load Diff
src/uu/csplit/src/csplit_error.rs
+37
View File
@@ -0,0 +1,37 @@
use std::io;
/// Errors thrown by the csplit command
#[derive(Debug, Fail)]
pub enum CsplitError {
#[fail(display = "IO error: {}", _0)]
IoError(io::Error),
#[fail(display = "'{}': line number out of range", _0)]
LineOutOfRange(String),
#[fail(display = "'{}': line number out of range on repetition {}", _0, _1)]
LineOutOfRangeOnRepetition(String, usize),
#[fail(display = "'{}': match not found", _0)]
MatchNotFound(String),
#[fail(display = "'{}': match not found on repetition {}", _0, _1)]
MatchNotFoundOnRepetition(String, usize),
#[fail(display = "line number must be greater than zero")]
LineNumberIsZero,
#[fail(
display = "line number '{}' is smaller than preceding line number, {}",
_0, _1
)]
LineNumberSmallerThanPrevious(usize, usize),
#[fail(display = "invalid pattern: {}", _0)]
InvalidPattern(String),
#[fail(display = "invalid number: '{}'", _0)]
InvalidNumber(String),
#[fail(display = "incorrect conversion specification in suffix")]
SuffixFormatIncorrect,
#[fail(display = "too many % conversion specifications in suffix")]
SuffixFormatTooManyPercents,
}
impl From<io::Error> for CsplitError {
fn from(error: io::Error) -> Self {
CsplitError::IoError(error)
}
}
src/uu/csplit/src/main.rs
+1
View File
@@ -0,0 +1 @@
uucore_procs::main!(uu_csplit); // spell-checker:ignore procs uucore
src/uu/csplit/src/patterns.rs
+355
View File
@@ -0,0 +1,355 @@
use crate::csplit_error::CsplitError;
use regex::Regex;
/// The definition of a pattern to match on a line.
#[derive(Debug)]
pub enum Pattern {
/// Copy the file's content to a split up to, not including, the given line number. The number
/// of times the pattern is executed is detailed in [`ExecutePattern`].
UpToLine(usize, ExecutePattern),
/// Copy the file's content to a split up to, not including, the line matching the regex. The
/// integer is an offset relative to the matched line of what to include (if positive) or
/// to exclude (if negative). The number of times the pattern is executed is detailed in
/// [`ExecutePattern`].
UpToMatch(Regex, i32, ExecutePattern),
/// Skip the file's content up to, not including, the line matching the regex. The integer
/// is an offset relative to the matched line of what to include (if positive) or to exclude
/// (if negative). The number of times the pattern is executed is detailed in [`ExecutePattern`].
SkipToMatch(Regex, i32, ExecutePattern),
}
impl ToString for Pattern {
fn to_string(&self) -> String {
match self {
Pattern::UpToLine(n, _) => n.to_string(),
Pattern::UpToMatch(regex, 0, _) => format!("/{}/", regex.as_str()),
Pattern::UpToMatch(regex, offset, _) => format!("/{}/{:+}", regex.as_str(), offset),
Pattern::SkipToMatch(regex, 0, _) => format!("%{}%", regex.as_str()),
Pattern::SkipToMatch(regex, offset, _) => format!("%{}%{:+}", regex.as_str(), offset),
}
}
}
/// The number of times a pattern can be used.
#[derive(Debug)]
pub enum ExecutePattern {
/// Execute the pattern as many times as possible
Always,
/// Execute the pattern a fixed number of times
Times(usize),
}
impl ExecutePattern {
pub fn iter(&self) -> ExecutePatternIter {
match self {
ExecutePattern::Times(n) => ExecutePatternIter::new(Some(*n)),
ExecutePattern::Always => ExecutePatternIter::new(None),
}
}
}
pub struct ExecutePatternIter {
max: Option<usize>,
cur: usize,
}
impl ExecutePatternIter {
fn new(max: Option<usize>) -> ExecutePatternIter {
ExecutePatternIter { max, cur: 0 }
}
}
impl Iterator for ExecutePatternIter {
type Item = (Option<usize>, usize);
fn next(&mut self) -> Option<(Option<usize>, usize)> {
match self.max {
// iterate until m is reached
Some(m) => {
if self.cur == m {
None
} else {
self.cur += 1;
Some((self.max, self.cur))
}
}
// no limit, just increment a counter
None => {
self.cur += 1;
Some((None, self.cur))
}
}
}
}
/// Parses the definitions of patterns given on the command line into a list of [`Pattern`]s.
///
/// # Errors
///
/// If a pattern is incorrect, a [`::CsplitError::InvalidPattern`] error is returned, which may be
/// due to, e.g.,:
/// - an invalid regular expression;
/// - an invalid number for, e.g., the offset.
pub fn get_patterns(args: &[String]) -> Result<Vec<Pattern>, CsplitError> {
let patterns = extract_patterns(args)?;
validate_line_numbers(&patterns)?;
Ok(patterns)
}
fn extract_patterns(args: &[String]) -> Result<Vec<Pattern>, CsplitError> {
let mut patterns = Vec::with_capacity(args.len());
let to_match_reg =
Regex::new(r"^(/(?P<UPTO>.+)/|%(?P<SKIPTO>.+)%)(?P<OFFSET>[\+-]\d+)?$").unwrap();
let execute_ntimes_reg = Regex::new(r"^\{(?P<TIMES>\d+)|\*\}$").unwrap();
let mut iter = args.iter().peekable();
while let Some(arg) = iter.next() {
// get the number of times a pattern is repeated, which is at least once plus whatever is
// in the quantifier.
let execute_ntimes = match iter.peek() {
None => ExecutePattern::Times(1),
Some(&next_item) => {
match execute_ntimes_reg.captures(next_item) {
None => ExecutePattern::Times(1),
Some(r) => {
// skip the next item
iter.next();
if let Some(times) = r.name("TIMES") {
ExecutePattern::Times(times.as_str().parse::<usize>().unwrap() + 1)
} else {
ExecutePattern::Always
}
}
}
}
};
// get the pattern definition
if let Some(captures) = to_match_reg.captures(arg) {
let offset = match captures.name("OFFSET") {
None => 0,
Some(m) => m.as_str().parse().unwrap(),
};
if let Some(up_to_match) = captures.name("UPTO") {
let pattern = match Regex::new(up_to_match.as_str()) {
Err(_) => {
return Err(CsplitError::InvalidPattern(arg.to_string()));
}
Ok(reg) => reg,
};
patterns.push(Pattern::UpToMatch(pattern, offset, execute_ntimes));
} else if let Some(skip_to_match) = captures.name("SKIPTO") {
let pattern = match Regex::new(skip_to_match.as_str()) {
Err(_) => {
return Err(CsplitError::InvalidPattern(arg.to_string()));
}
Ok(reg) => reg,
};
patterns.push(Pattern::SkipToMatch(pattern, offset, execute_ntimes));
}
} else if let Ok(line_number) = arg.parse::<usize>() {
patterns.push(Pattern::UpToLine(line_number, execute_ntimes));
} else {
return Err(CsplitError::InvalidPattern(arg.to_string()));
}
}
Ok(patterns)
}
/// Asserts the line numbers are in increasing order, starting at 1.
fn validate_line_numbers(patterns: &[Pattern]) -> Result<(), CsplitError> {
patterns
.iter()
.filter_map(|pattern| match pattern {
Pattern::UpToLine(line_number, _) => Some(line_number),
_ => None,
})
.try_fold(0, |prev_ln, &current_ln| match (prev_ln, current_ln) {
// a line number cannot be zero
(_, 0) => Err(CsplitError::LineNumberIsZero),
// two consecutifs numbers should not be equal
(n, m) if n == m => {
show_warning!("line number '{}' is the same as preceding line number", n);
Ok(n)
}
// a number cannot be greater than the one that follows
(n, m) if n > m => Err(CsplitError::LineNumberSmallerThanPrevious(m, n)),
(_, m) => Ok(m),
})?;
Ok(())
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn bad_pattern() {
let input = vec!["bad".to_string()];
assert!(get_patterns(input.as_slice()).is_err());
}
#[test]
fn up_to_line_pattern() {
let input: Vec<String> = vec!["24", "42", "{*}", "50", "{4}"]
.into_iter()
.map(|v| v.to_string())
.collect();
let patterns = get_patterns(input.as_slice()).unwrap();
assert_eq!(patterns.len(), 3);
match patterns.get(0) {
Some(Pattern::UpToLine(24, ExecutePattern::Times(1))) => (),
_ => panic!("expected UpToLine pattern"),
};
match patterns.get(1) {
Some(Pattern::UpToLine(42, ExecutePattern::Always)) => (),
_ => panic!("expected UpToLine pattern"),
};
match patterns.get(2) {
Some(Pattern::UpToLine(50, ExecutePattern::Times(5))) => (),
_ => panic!("expected UpToLine pattern"),
};
}
#[test]
fn up_to_match_pattern() {
let input: Vec<String> = vec![
"/test1.*end$/",
"/test2.*end$/",
"{*}",
"/test3.*end$/",
"{4}",
"/test4.*end$/+3",
"/test5.*end$/-3",
]
.into_iter()
.map(|v| v.to_string())
.collect();
let patterns = get_patterns(input.as_slice()).unwrap();
assert_eq!(patterns.len(), 5);
match patterns.get(0) {
Some(Pattern::UpToMatch(reg, 0, ExecutePattern::Times(1))) => {
let parsed_reg = format!("{}", reg);
assert_eq!(parsed_reg, "test1.*end$");
}
_ => panic!("expected UpToMatch pattern"),
};
match patterns.get(1) {
Some(Pattern::UpToMatch(reg, 0, ExecutePattern::Always)) => {
let parsed_reg = format!("{}", reg);
assert_eq!(parsed_reg, "test2.*end$");
}
_ => panic!("expected UpToMatch pattern"),
};
match patterns.get(2) {
Some(Pattern::UpToMatch(reg, 0, ExecutePattern::Times(5))) => {
let parsed_reg = format!("{}", reg);
assert_eq!(parsed_reg, "test3.*end$");
}
_ => panic!("expected UpToMatch pattern"),
};
match patterns.get(3) {
Some(Pattern::UpToMatch(reg, 3, ExecutePattern::Times(1))) => {
let parsed_reg = format!("{}", reg);
assert_eq!(parsed_reg, "test4.*end$");
}
_ => panic!("expected UpToMatch pattern"),
};
match patterns.get(4) {
Some(Pattern::UpToMatch(reg, -3, ExecutePattern::Times(1))) => {
let parsed_reg = format!("{}", reg);
assert_eq!(parsed_reg, "test5.*end$");
}
_ => panic!("expected UpToMatch pattern"),
};
}
#[test]
fn skip_to_match_pattern() {
let input: Vec<String> = vec![
"%test1.*end$%",
"%test2.*end$%",
"{*}",
"%test3.*end$%",
"{4}",
"%test4.*end$%+3",
"%test5.*end$%-3",
]
.into_iter()
.map(|v| v.to_string())
.collect();
let patterns = get_patterns(input.as_slice()).unwrap();
assert_eq!(patterns.len(), 5);
match patterns.get(0) {
Some(Pattern::SkipToMatch(reg, 0, ExecutePattern::Times(1))) => {
let parsed_reg = format!("{}", reg);
assert_eq!(parsed_reg, "test1.*end$");
}
_ => panic!("expected SkipToMatch pattern"),
};
match patterns.get(1) {
Some(Pattern::SkipToMatch(reg, 0, ExecutePattern::Always)) => {
let parsed_reg = format!("{}", reg);
assert_eq!(parsed_reg, "test2.*end$");
}
_ => panic!("expected SkipToMatch pattern"),
};
match patterns.get(2) {
Some(Pattern::SkipToMatch(reg, 0, ExecutePattern::Times(5))) => {
let parsed_reg = format!("{}", reg);
assert_eq!(parsed_reg, "test3.*end$");
}
_ => panic!("expected SkipToMatch pattern"),
};
match patterns.get(3) {
Some(Pattern::SkipToMatch(reg, 3, ExecutePattern::Times(1))) => {
let parsed_reg = format!("{}", reg);
assert_eq!(parsed_reg, "test4.*end$");
}
_ => panic!("expected SkipToMatch pattern"),
};
match patterns.get(4) {
Some(Pattern::SkipToMatch(reg, -3, ExecutePattern::Times(1))) => {
let parsed_reg = format!("{}", reg);
assert_eq!(parsed_reg, "test5.*end$");
}
_ => panic!("expected SkipToMatch pattern"),
};
}
#[test]
fn line_number_zero() {
let patterns = vec![Pattern::UpToLine(0, ExecutePattern::Times(1))];
match validate_line_numbers(&patterns) {
Err(CsplitError::LineNumberIsZero) => (),
_ => panic!("expected LineNumberIsZero error"),
}
}
#[test]
fn line_number_smaller_than_previous() {
let input: Vec<String> = vec!["10".to_string(), "5".to_string()];
match get_patterns(input.as_slice()) {
Err(CsplitError::LineNumberSmallerThanPrevious(5, 10)) => (),
_ => panic!("expected LineNumberSmallerThanPrevious error"),
}
}
#[test]
fn line_number_smaller_than_previous_separate() {
let input: Vec<String> = vec!["10".to_string(), "/20/".to_string(), "5".to_string()];
match get_patterns(input.as_slice()) {
Err(CsplitError::LineNumberSmallerThanPrevious(5, 10)) => (),
_ => panic!("expected LineNumberSmallerThanPrevious error"),
}
}
#[test]
fn line_number_zero_separate() {
let input: Vec<String> = vec!["10".to_string(), "/20/".to_string(), "0".to_string()];
match get_patterns(input.as_slice()) {
Err(CsplitError::LineNumberIsZero) => (),
_ => panic!("expected LineNumberIsZero error"),
}
}
}
src/uu/csplit/src/splitname.rs
+395
View File
@@ -0,0 +1,395 @@
use regex::Regex;
use crate::csplit_error::CsplitError;
/// Computes the filename of a split, taking into consideration a possible user-defined suffix
/// format.
pub struct SplitName {
fn_split_name: Box<dyn Fn(usize) -> String>,
}
impl SplitName {
/// Creates a new SplitName with the given user-defined options:
/// - `prefix_opt` specifies a prefix for all splits.
/// - `format_opt` specifies a custom format for the suffix part of the filename, using the
/// `sprintf` format notation.
/// - `n_digits_opt` defines the width of the split number.
///
/// # Caveats
///
/// If `prefix_opt` and `format_opt` are defined, and the `format_opt` has some string appearing
/// before the conversion pattern (e.g., "here-%05d"), then it is appended to the passed prefix
/// via `prefix_opt`.
///
/// If `n_digits_opt` and `format_opt` are defined, then width defined in `format_opt` is
/// taken.
pub fn new(
prefix_opt: Option<String>,
format_opt: Option<String>,
n_digits_opt: Option<String>,
) -> Result<SplitName, CsplitError> {
// get the prefix
let prefix = prefix_opt.unwrap_or_else(|| "xx".to_string());
// the width for the split offset
let n_digits = match n_digits_opt {
None => 2,
Some(opt) => match opt.parse::<usize>() {
Ok(digits) => digits,
Err(_) => return Err(CsplitError::InvalidNumber(opt)),
},
};
// translate the custom format into a function
let fn_split_name: Box<dyn Fn(usize) -> String> = match format_opt {
None => Box::new(move |n: usize| -> String {
format!("{}{:0width$}", prefix, n, width = n_digits)
}),
Some(custom) => {
let spec =
Regex::new(r"(?P<ALL>%(?P<FLAG>[0#-])(?P<WIDTH>\d+)?(?P<TYPE>[diuoxX]))")
.unwrap();
let mut captures_iter = spec.captures_iter(&custom);
let custom_fn: Box<dyn Fn(usize) -> String> = match captures_iter.next() {
Some(captures) => {
let all = captures.name("ALL").unwrap();
let before = custom[0..all.start()].to_owned();
let after = custom[all.end()..].to_owned();
let n_digits = match captures.name("WIDTH") {
None => 0,
Some(m) => m.as_str().parse::<usize>().unwrap(),
};
match (captures.name("FLAG"), captures.name("TYPE")) {
(Some(ref f), Some(ref t)) => {
match (f.as_str(), t.as_str()) {
/*
* zero padding
*/
// decimal
("0", "d") | ("0", "i") | ("0", "u") => {
Box::new(move |n: usize| -> String {
format!(
"{}{}{:0width$}{}",
prefix,
before,
n,
after,
width = n_digits
)
})
}
// octal
("0", "o") => Box::new(move |n: usize| -> String {
format!(
"{}{}{:0width$o}{}",
prefix,
before,
n,
after,
width = n_digits
)
}),
// lower hexadecimal
("0", "x") => Box::new(move |n: usize| -> String {
format!(
"{}{}{:0width$x}{}",
prefix,
before,
n,
after,
width = n_digits
)
}),
// upper hexadecimal
("0", "X") => Box::new(move |n: usize| -> String {
format!(
"{}{}{:0width$X}{}",
prefix,
before,
n,
after,
width = n_digits
)
}),
/*
* Alternate form
*/
// octal
("#", "o") => Box::new(move |n: usize| -> String {
format!(
"{}{}{:>#width$o}{}",
prefix,
before,
n,
after,
width = n_digits
)
}),
// lower hexadecimal
("#", "x") => Box::new(move |n: usize| -> String {
format!(
"{}{}{:>#width$x}{}",
prefix,
before,
n,
after,
width = n_digits
)
}),
// upper hexadecimal
("#", "X") => Box::new(move |n: usize| -> String {
format!(
"{}{}{:>#width$X}{}",
prefix,
before,
n,
after,
width = n_digits
)
}),
/*
* Left adjusted
*/
// decimal
("-", "d") | ("-", "i") | ("-", "u") => {
Box::new(move |n: usize| -> String {
format!(
"{}{}{:<#width$}{}",
prefix,
before,
n,
after,
width = n_digits
)
})
}
// octal
("-", "o") => Box::new(move |n: usize| -> String {
format!(
"{}{}{:<#width$o}{}",
prefix,
before,
n,
after,
width = n_digits
)
}),
// lower hexadecimal
("-", "x") => Box::new(move |n: usize| -> String {
format!(
"{}{}{:<#width$x}{}",
prefix,
before,
n,
after,
width = n_digits
)
}),
// upper hexadecimal
("-", "X") => Box::new(move |n: usize| -> String {
format!(
"{}{}{:<#width$X}{}",
prefix,
before,
n,
after,
width = n_digits
)
}),
_ => return Err(CsplitError::SuffixFormatIncorrect),
}
}
_ => return Err(CsplitError::SuffixFormatIncorrect),
}
}
None => return Err(CsplitError::SuffixFormatIncorrect),
};
// there cannot be more than one format pattern
if captures_iter.next().is_some() {
return Err(CsplitError::SuffixFormatTooManyPercents);
}
custom_fn
}
};
Ok(SplitName { fn_split_name })
}
/// Returns the filename of the i-th split.
pub fn get(&self, n: usize) -> String {
(self.fn_split_name)(n)
}
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn invalid_number() {
let split_name = SplitName::new(None, None, Some(String::from("bad")));
match split_name {
Err(CsplitError::InvalidNumber(_)) => (),
_ => panic!("should fail with InvalidNumber"),
};
}
#[test]
fn invalid_suffix_format1() {
let split_name = SplitName::new(None, Some(String::from("no conversion string")), None);
match split_name {
Err(CsplitError::SuffixFormatIncorrect) => (),
_ => panic!("should fail with SuffixFormatIncorrect"),
};
}
#[test]
fn invalid_suffix_format2() {
let split_name = SplitName::new(None, Some(String::from("%042a")), None);
match split_name {
Err(CsplitError::SuffixFormatIncorrect) => (),
_ => panic!("should fail with SuffixFormatIncorrect"),
};
}
#[test]
fn default_formatter() {
let split_name = SplitName::new(None, None, None).unwrap();
assert_eq!(split_name.get(2), "xx02");
}
#[test]
fn default_formatter_with_prefix() {
let split_name = SplitName::new(Some(String::from("aaa")), None, None).unwrap();
assert_eq!(split_name.get(2), "aaa02");
}
#[test]
fn default_formatter_with_width() {
let split_name = SplitName::new(None, None, Some(String::from("5"))).unwrap();
assert_eq!(split_name.get(2), "xx00002");
}
#[test]
fn zero_padding_decimal1() {
let split_name = SplitName::new(None, Some(String::from("cst-%03d-")), None).unwrap();
assert_eq!(split_name.get(2), "xxcst-002-");
}
#[test]
fn zero_padding_decimal2() {
let split_name = SplitName::new(
Some(String::from("pre-")),
Some(String::from("cst-%03d-post")),
None,
)
.unwrap();
assert_eq!(split_name.get(2), "pre-cst-002-post");
}
#[test]
fn zero_padding_decimal3() {
let split_name = SplitName::new(
None,
Some(String::from("cst-%03d-")),
Some(String::from("42")),
)
.unwrap();
assert_eq!(split_name.get(2), "xxcst-002-");
}
#[test]
fn zero_padding_decimal4() {
let split_name = SplitName::new(None, Some(String::from("cst-%03i-")), None).unwrap();
assert_eq!(split_name.get(2), "xxcst-002-");
}
#[test]
fn zero_padding_decimal5() {
let split_name = SplitName::new(None, Some(String::from("cst-%03u-")), None).unwrap();
assert_eq!(split_name.get(2), "xxcst-002-");
}
#[test]
fn zero_padding_octal() {
let split_name = SplitName::new(None, Some(String::from("cst-%03o-")), None).unwrap();
assert_eq!(split_name.get(42), "xxcst-052-");
}
#[test]
fn zero_padding_lower_hexa() {
let split_name = SplitName::new(None, Some(String::from("cst-%03x-")), None).unwrap();
assert_eq!(split_name.get(42), "xxcst-02a-");
}
#[test]
fn zero_padding_upper_hexa() {
let split_name = SplitName::new(None, Some(String::from("cst-%03X-")), None).unwrap();
assert_eq!(split_name.get(42), "xxcst-02A-");
}
#[test]
fn alternate_form_octal() {
let split_name = SplitName::new(None, Some(String::from("cst-%#10o-")), None).unwrap();
assert_eq!(split_name.get(42), "xxcst- 0o52-");
}
#[test]
fn alternate_form_lower_hexa() {
let split_name = SplitName::new(None, Some(String::from("cst-%#10x-")), None).unwrap();
assert_eq!(split_name.get(42), "xxcst- 0x2a-");
}
#[test]
fn alternate_form_upper_hexa() {
let split_name = SplitName::new(None, Some(String::from("cst-%#10X-")), None).unwrap();
assert_eq!(split_name.get(42), "xxcst- 0x2A-");
}
#[test]
fn left_adjusted_decimal1() {
let split_name = SplitName::new(None, Some(String::from("cst-%-10d-")), None).unwrap();
assert_eq!(split_name.get(42), "xxcst-42 -");
}
#[test]
fn left_adjusted_decimal2() {
let split_name = SplitName::new(None, Some(String::from("cst-%-10i-")), None).unwrap();
assert_eq!(split_name.get(42), "xxcst-42 -");
}
#[test]
fn left_adjusted_decimal3() {
let split_name = SplitName::new(None, Some(String::from("cst-%-10u-")), None).unwrap();
assert_eq!(split_name.get(42), "xxcst-42 -");
}
#[test]
fn left_adjusted_octal() {
let split_name = SplitName::new(None, Some(String::from("cst-%-10o-")), None).unwrap();
assert_eq!(split_name.get(42), "xxcst-0o52 -");
}
#[test]
fn left_adjusted_lower_hexa() {
let split_name = SplitName::new(None, Some(String::from("cst-%-10x-")), None).unwrap();
assert_eq!(split_name.get(42), "xxcst-0x2a -");
}
#[test]
fn left_adjusted_upper_hexa() {
let split_name = SplitName::new(None, Some(String::from("cst-%-10X-")), None).unwrap();
assert_eq!(split_name.get(42), "xxcst-0x2A -");
}
#[test]
fn too_many_percent() {
let split_name = SplitName::new(None, Some(String::from("%02d-%-3x")), None);
match split_name {
Err(CsplitError::SuffixFormatTooManyPercents) => (),
_ => panic!("should fail with SuffixFormatTooManyPercents"),
};
}
}
tests/by-util/test_csplit.rs
+1335
View File
File diff suppressed because it is too large Load Diff
tests/fixtures/csplit/numbers50.txt
Vendored
+50
View File
@@ -0,0 +1,50 @@
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50