Merge #1007 (regex support for expr) with latest master

Cargo.toml

@@ -241,7 +241,7 @@ yes      = { optional=true, path="src/yes" }
 time = "0.1.38"
 filetime = "0.1.10"
 libc = "0.2.26"
-regex = "0.1.80"
+regex = "0.2.2"
 rand = "0.3.15"
 tempdir = "0.3.5"
 unindent = "0.1.0"

README.md

@@ -151,7 +151,7 @@ Utilities
 | Done      | Semi-Done | To Do  |
 |-----------|-----------|--------|
 | arch      | cp        | chcon  |
-| base32    | expr (no regular expressions) | csplit |
+| base32    | expr | csplit |
 | base64    | install   | dd     |
 | basename  | ls        | df     |
 | cat       | more      | join   |

appveyor.yml

@@ -1,7 +1,15 @@
+os: Visual Studio 2015
+
 environment:
   matrix:
   - TARGET: x86_64-pc-windows-msvc
+    MSYS_BITS: 64
+    TOOLCHAIN: msvc
+    PLATFORM: x86_64
   - TARGET: i686-pc-windows-msvc
+    MSYS_BITS: 32
+    TOOLCHAIN: msvc
+    PLATFORM: i686
   - TARGET: i686-pc-windows-gnu
     MINGW_URL: https://sourceforge.net/projects/mingw-w64/files/Toolchains%20targetting%20Win32/Personal%20Builds/mingw-builds/4.9.2/threads-win32/dwarf/i686-4.9.2-release-win32-dwarf-rt_v4-rev4.7z/download
     MINGW_ARCHIVE: i686-4.9.2-release-win32-dwarf-rt_v4-rev4.7z
@@ -33,6 +41,9 @@ install:
 
   - rustc -V
   - cargo -V
+  - if "%TOOLCHAIN%" == "msvc" if "%PLATFORM%" == "i686" call "%VS140COMNTOOLS%\..\..\VC\vcvarsall.bat"
+  - if "%TOOLCHAIN%" == "msvc" if "%PLATFORM%" == "x86_64" "C:\Program Files\Microsoft SDKs\Windows\v7.1\Bin\SetEnv.cmd" /x64
+  - if "%TOOLCHAIN%" == "msvc" if "%PLATFORM%" == "x86_64" call "%VS140COMNTOOLS%\..\..\VC\vcvarsall.bat" x86_amd64
 
 artifacts:
   - path: target\debug\uutils.exe

src/date/Cargo.toml

@@ -8,7 +8,7 @@ name = "uu_date"
 path = "date.rs"
 
 [dependencies]
-chrono = "0.3.0"
+chrono = "0.4.0"
 clap = "2.24.1"
 uucore = { path="../uucore" }
 

src/date/date.rs

@@ -15,7 +15,7 @@ extern crate clap;
 extern crate uucore;
 
 use chrono::{DateTime, FixedOffset, Offset, Local};
-use chrono::offset::utc::UTC;
+use chrono::offset::Utc;
 use std::fs::File;
 use std::io::{BufRead, BufReader};
 use std::path::PathBuf;
@@ -123,7 +123,7 @@ pub fn uumain(args: Vec<String>) -> i32 {
         // Get the current time, either in the local time zone or UTC.
         let now: DateTime<FixedOffset> = match settings.utc {
             true => {
-                let now = UTC::now();
+                let now = Utc::now();
                 now.with_timezone(&now.offset().fix())
             }
             false => {

src/expr/Cargo.toml

@@ -9,6 +9,7 @@ path = "expr.rs"
 
 [dependencies]
 libc = "0.2.26"
+onig = "1.3.0"
 uucore = { path="../uucore" }
 
 [[bin]]

src/expr/expr.rs

@@ -11,6 +11,7 @@
 
 #[macro_use]
 extern crate uucore;
+extern crate onig;
 
 mod tokens;
 mod syntax_tree;
@@ -95,9 +96,9 @@ separates increasing precedence groups.  EXPRESSION may be:
   ARG1 / ARG2       arithmetic quotient of ARG1 divided by ARG2
   ARG1 % ARG2       arithmetic remainder of ARG1 divided by ARG2
 
-  STRING : REGEXP   [NOT IMPLEMENTED] anchored pattern match of REGEXP in STRING
+  STRING : REGEXP   anchored pattern match of REGEXP in STRING
 
-  match STRING REGEXP        [NOT IMPLEMENTED] same as STRING : REGEXP
+  match STRING REGEXP        same as STRING : REGEXP
   substr STRING POS LENGTH   substring of STRING, POS counted from 1
   index STRING CHARS         index in STRING where any CHARS is found, or 0
   length STRING              length of STRING

src/expr/syntax_tree.rs

@@ -13,6 +13,7 @@
 //!
 
 use tokens::{Token};
+use onig::{Regex, Syntax, REGEX_OPTION_NONE};
 
 type TokenStack = Vec<(usize, Token)>;
 pub type OperandsList = Vec< Box<ASTNode> >;
@@ -105,6 +106,7 @@ impl ASTNode {
                                 ),
                             "|" => infix_operator_or(&operand_values),
                             "&" => infix_operator_and(&operand_values),
+                            ":" | "match" => operator_match(&operand_values),
                             "length" => prefix_operator_length( &operand_values ),
                             "index" => prefix_operator_index( &operand_values ),
                             "substr" => prefix_operator_substr( &operand_values ),
@@ -350,6 +352,25 @@ fn infix_operator_and( values: &Vec<String> ) -> Result<String, String> {
     }
 }
 
+fn operator_match(values: &Vec<String>) -> Result<String, String> {
+    assert!(values.len() == 2);
+    let re = match Regex::with_options(&values[1], REGEX_OPTION_NONE, Syntax::grep()) {
+        Ok(m) => m,
+        Err(err) => return Err(err.description().to_string())
+    };
+    if re.captures_len() > 0 {
+        Ok(match re.captures(&values[0]) {
+            Some(captures) => captures.at(1).unwrap().to_string(),
+            None => "".to_string()
+        })
+    } else {
+        Ok(match re.find(&values[0]) {
+            Some((start, end)) => (end - start).to_string(),
+            None => "0".to_string()
+        })
+    }
+}
+
 fn prefix_operator_length( values: &Vec<String> ) -> Result<String, String> {
     assert!( values.len() == 1 );
     Ok( values[0].len().to_string() )

src/hashsum/Cargo.toml

@@ -10,7 +10,7 @@ path = "hashsum.rs"
 [dependencies]
 getopts = "0.2.14"
 libc = "0.2.26"
-regex = "0.1.80"
+regex = "0.2.2"
 regex-syntax = "0.4.1"
 rust-crypto = "0.2.36"
 rustc-serialize = "0.3.24"

src/hashsum/hashsum.rs

@@ -295,12 +295,12 @@ fn hashsum(algoname: &str, mut digest: Box<Digest>, files: Vec<String>, binary:
             for (i, line) in buffer.lines().enumerate() {
                 let line = safe_unwrap!(line);
                 let (ck_filename, sum, binary_check) = match gnu_re.captures(&line) {
-                    Some(caps) => (caps.name("fileName").unwrap(),
-                                   caps.name("digest").unwrap().to_ascii_lowercase(),
-                                   caps.name("binary").unwrap() == "*"),
+                    Some(caps) => (caps.name("fileName").unwrap().as_str(),
+                                   caps.name("digest").unwrap().as_str().to_ascii_lowercase(),
+                                   caps.name("binary").unwrap().as_str() == "*"),
                     None => match bsd_re.captures(&line) {
-                        Some(caps) => (caps.name("fileName").unwrap(),
-                                       caps.name("digest").unwrap().to_ascii_lowercase(),
+                        Some(caps) => (caps.name("fileName").unwrap().as_str(),
+                                       caps.name("digest").unwrap().as_str().to_ascii_lowercase(),
                                        true),
                         None => {
                             bad_format += 1;

src/ptx/Cargo.toml

@@ -13,7 +13,7 @@ libc = "0.2.26"
 aho-corasick = "0.6.3"
 memchr = "1.0.1"
 regex-syntax = "0.4.1"
-regex = "0.1.80"
+regex = "0.2.2"
 uucore = { path="../uucore" }
 
 [[bin]]

src/ptx/ptx.rs

@@ -237,11 +237,12 @@ fn create_word_set(config: &Config, filter: &WordFilter,
         for line in &lines.0 {
             // if -r, exclude reference from word set
             let (ref_beg, ref_end) = match ref_reg.find(line) {
-                Some(x) => x,
-                None => (0,0)
+                Some(x) => (x.start(), x.end()),
+                None => (0, 0)
             };
             // match words with given regex
-            for (beg, end) in reg.find_iter(line) {
+            for mat in reg.find_iter(line) {
+                let (beg, end) = (mat.start(), mat.end());
                 if config.input_ref && ((beg, end) == (ref_beg, ref_end)) {
                     continue;
                 }
@@ -279,8 +280,8 @@ fn get_reference(config: &Config, word_ref: &WordRef, line: &str) ->
     } else if config.input_ref {
         let reg = Regex::new(&config.context_regex).unwrap();
         let (beg, end) = match reg.find(line) {
-            Some(x) => x,
-            None => (0,0)
+            Some(x) => (x.start(), x.end()),
+            None => (0, 0)
         };
         format!("{}", &line[beg .. end])
     } else {

tests/test_split.rs

@@ -93,7 +93,7 @@ impl RandomFile {
 fn test_split_default() {
     let (at, mut ucmd) = at_and_ucmd!();
     let name = "split_default";
-    let glob = Glob::new(&at, ".", r"x[:alpha:][:alpha:]$");
+    let glob = Glob::new(&at, ".", r"x[[:alpha:]][[:alpha:]]$");
     RandomFile::new(&at, name).add_lines(2000);
     ucmd.args(&[name]).succeeds();
     assert_eq!(glob.count(), 2);
@@ -115,7 +115,7 @@ fn test_split_num_prefixed_chunks_by_bytes() {
 fn test_split_str_prefixed_chunks_by_bytes() {
     let (at, mut ucmd) = at_and_ucmd!();
     let name = "split_str_prefixed_chunks_by_bytes";
-    let glob = Glob::new(&at, ".", r"b[:alpha:][:alpha:]$");
+    let glob = Glob::new(&at, ".", r"b[[:alpha:]][[:alpha:]]$");
     RandomFile::new(&at, name).add_bytes(10000);
     ucmd.args(&["-b", "1000", name, "b"]).succeeds();
     assert_eq!(glob.count(), 10);
@@ -137,7 +137,7 @@ fn test_split_num_prefixed_chunks_by_lines() {
 fn test_split_str_prefixed_chunks_by_lines() {
     let (at, mut ucmd) = at_and_ucmd!();
     let name = "split_str_prefixed_chunks_by_lines";
-    let glob = Glob::new(&at, ".", r"d[:alpha:][:alpha:]$");
+    let glob = Glob::new(&at, ".", r"d[[:alpha:]][[:alpha:]]$");
     RandomFile::new(&at, name).add_lines(10000);
     ucmd.args(&["-l", "1000", name, "d"]).succeeds();
     assert_eq!(glob.count(), 10);