Merge pull request #2 from kemitix/ignore-extra-tokens

Add support to ignore extra tokens on a line

.gitignore

@@ -5,3 +5,4 @@ deps.zig
 /test.in
 /test.out
 /test.expect
+/dist

Makefile

@@ -0,0 +1,15 @@
+dist: inttest
+	mkdir dist
+	cp zig-out/bin/skip dist/
+
+inttest: zig-out/bin/skip
+	./test.sh
+
+zig-out/bin/skip: unittest
+	zig build
+
+unittest: zigmod src/main.zig
+	zig build test
+
+zigmod: zig.mod
+	zigmod ci

README.md

@@ -42,6 +42,8 @@ line 4
 
 ### Skip until a number of matching lines
 
+The whole line must match.
+
 This example reads the named file.
 
 File: `input.txt`
@@ -67,7 +69,9 @@ gamma
 alpha
 ```
 
-### Skip lines until a number of tokens as seen
+### Skip lines until a number of tokens are seen
+
+Looks for a string within a line, counting each occurance.
 
 This example reads the file from stdin.
 
@@ -99,3 +103,44 @@ commodo consequat.
 
 It matches the first `dolor` on line 1,
  and the second on line 4 as part of the word `dolore`.
+
+### Skip lines until a lines with tokens are seen
+
+Looks for a string within a line, only counting each matching line once.
+
+This example reads the file from stdin.
+
+File: `input.txt`
+
+```text
+Lorem ipsum dolor sit amet, 
+consectetur adipiscing elit, 
+sed do eiusmod tempor incididunt 
+ut labore et dolore magna aliqua. 
+Ut enim ad minim veniam, 
+quis nostrud exercitation ullamco 
+laboris nisi ut aliquip ex ea 
+commodo consequat. 
+```
+
+```bash
+cat input.txt | skip 4 --token m --ignore-extras
+```
+
+Will output:
+
+```text
+quis nostrud exercitation ullamco 
+laboris nisi ut aliquip ex ea 
+commodo consequat. 
+```
+
+Without `--ignore-extras`, it would have found the fourth `m` on line 3, and displayed:
+
+```text
+ut labore et dolore magna aliqua. 
+Ut enim ad minim veniam, 
+quis nostrud exercitation ullamco 
+laboris nisi ut aliquip ex ea 
+commodo consequat. 
+```

src/main.zig

@@ -11,12 +11,6 @@ const clap = @import("clap");
 
 const version = "0.1.0";
 
-// step 1: [x] read in a file from stdin and write out to stdout
-// step 2: [x] read in a named file in parameters and write out to stdout
-// step 3: [x] skip a number of lines
-// step 4: [ ] skip a number of matching lines
-// step 5: [ ] skip a number of tokens
-
 const maxLineLength = 4096;
 
 pub fn main() anyerror!void {
@@ -52,6 +46,7 @@ const Config = struct {
     file: ?fs.File,
     line: ?[]const u8 = null,
     token: ?[]const u8 = null,
+    ignoreExtras: bool,
 
     pub fn deinit(self: @This()) void {
         if (self.file) |f| {
@@ -62,17 +57,18 @@ const Config = struct {
 
 fn parseArgs(allocator: mem.Allocator) !Config {
     const params = comptime [_]clap.Param(clap.Help) {
-        clap.parseParam("<N>               The number of lines to skip") catch unreachable,
+        clap.parseParam("<N>                 The number of lines to skip") catch unreachable,
-        clap.parseParam("[<FILE>]          The file to read or stdin if not given") catch unreachable,
+        clap.parseParam("[<FILE>]            The file to read or stdin if not given") catch unreachable,
-        clap.parseParam("-l, --line <STR>  Skip until N lines matching this") catch unreachable,
+        clap.parseParam("-l, --line <STR>    Skip until N lines matching this") catch unreachable,
-        clap.parseParam("-t, --token <STR> Skip lines until N tokens found") catch unreachable,
+        clap.parseParam("-t, --token <STR>   Skip lines until N tokens found") catch unreachable,
-        clap.parseParam("-h, --help        Display this help and exit") catch unreachable,
+        clap.parseParam("-i, --ignore-extras Only count the first token on each line") catch unreachable,
-        clap.parseParam("-v, --version     Display the version") catch unreachable,
+        clap.parseParam("-h, --help          Display this help and exit") catch unreachable,
+        clap.parseParam("-v, --version       Display the version") catch unreachable,
     };
     var diag = clap.Diagnostic{};
     var args = clap.parse(clap.Help, &params, .{ .diagnostic = &diag }) catch |err| {
         diag.report(io.getStdErr().writer(), err) catch {};
-        return err;
+        return error.BadArgs;
     };
     defer args.deinit();
 
@@ -103,6 +99,15 @@ fn parseArgs(allocator: mem.Allocator) !Config {
     if (args.option("--token")) |match| {
         token = try allocator.dupe(u8, match);
     }
+    var ignoreExtras: bool = false;
+    if (args.flag("--ignore-extras")) {
+        if (token) |_| {
+            ignoreExtras = true;
+        } else {
+            try io.getStdErr().writer().print("Error: --ignore-extras requires --token\n", .{});
+            return error.BadArgs;
+        }
+    }
 
     var n: u32 = 0;
     var file: ?fs.File = null;
@@ -128,6 +133,7 @@ fn parseArgs(allocator: mem.Allocator) !Config {
         .file = file,
         .line = line,
         .token = token,
+        .ignoreExtras = ignoreExtras,
     };
 }
 
@@ -138,22 +144,23 @@ fn dumpInput(config: Config, in: fs.File, out: fs.File, allocator: mem.Allocator
     var c: usize = 0;
     while (c < config.lines) {
         const line = it.next();
-        if (config.line) |match| {
+        if (line) |memory| {
-            if (line) |memory| {
+            if (config.line) |match| {
                 if (mem.eql(u8, match, memory)) {
                     c += 1;
                 }
-            }
-        } else {
-            if (config.token) |token| {
-                if (line) |memory| {
-                    c += mem.count(u8, memory, token);
-                }
             } else {
-                c += 1;
+                if (config.token) |token| {
+                    const occurances = mem.count(u8, memory, token);
+                    if (config.ignoreExtras and occurances > 0) {
+                        c += 1;
+                    } else {
+                        c += occurances;
+                    }
+                } else {
+                    c += 1;
+                }
             }
-        }
-        if (line) |memory| {
             allocator.free(memory);
         } else return;
     }
@@ -172,6 +179,7 @@ test "dumpInput skip 1 line" {
     const config = Config{
         .lines = 1,
         .file = file,
+        .ignoreExtras = false,
     };
 
     try dumpInput(config, file, output, testing.allocator);
@@ -202,6 +210,7 @@ test "dumpInput skip 2 line 'alpha'" {
         .lines = 2,
         .file = file,
         .line = "alpha",
+        .ignoreExtras = false,
     };
 
     try dumpInput(config, file, output, testing.allocator);

test.sh

@@ -2,6 +2,14 @@
 
 set -e
 
+SKIP="./zig-out/bin/skip"
+DIFF="diff -u --color"
+
+if test ! -x $SKIP ; then
+    echo "File missing: $SKIP - try 'zig build'"
+    exit 1
+fi
+
 echo "> skip a line when reading from stdin"
 INPUT=$(cat<<EOF
 line 1
@@ -9,8 +17,9 @@ line 2
 EOF
 )
 echo "line 2" > test.expect
-echo "$INPUT" | ./skip 1 > test.out
+echo "$INPUT" | $SKIP 1 > test.out
-diff --brief test.expect test.out
+$DIFF test.expect test.out
+rm test.expect test.out
 
 echo "> skip a line when reading from a file"
 cat<<EOF > test.in
@@ -18,8 +27,9 @@ line 1
 line 2
 EOF
 echo "line 2" > test.expect
-./skip 1 test.in > test.out
+$SKIP 1 test.in > test.out
-diff --brief test.expect test.out
+$DIFF test.expect test.out
+rm test.expect test.out
 
 echo "> skip until 2 matching lines seen"
 cat<<EOF > test.in
@@ -35,8 +45,9 @@ alpha
 gamma
 alpha
 EOF
-./skip 2 test.in --line alpha > test.out
+$SKIP 2 test.in --line alpha > test.out
-diff --brief test.expect test.out
+$DIFF test.expect test.out
+rm test.in test.expect test.out
 
 echo "> skip lines until 2 tokens seen"
 cat<<EOF > test.in
@@ -55,9 +66,54 @@ quis nostrud exercitation ullamco
 laboris nisi ut aliquip ex ea 
 commodo consequat. 
 EOF
-./skip 2 test.in --token dolor > test.out
+$SKIP 2 test.in --token dolor > test.out 2
-diff --brief test.expect test.out
+$DIFF test.expect test.out
+rm test.in test.expect test.out
 
-rm test.in test.out test.expect
+echo "> handle unknown parameter with simple error message"
+cat<<EOF > test.expect.err
+Invalid argument '--foo'
+EOF
+cat<<EOF > test.expect
+EOF
+touch test.out test.err
+$SKIP --foo > test.out 2> test.err
+$DIFF test.expect test.out
+$DIFF test.expect.err test.err
+rm test.expect test.out
+rm test.expect.err test.err
+
+echo "> handle ignore-extra when token is missing"
+cat<<EOF > test.expect.err
+Error: --ignore-extras requires --token
+EOF
+cat<<EOF > test.expect
+EOF
+touch test.out test.err
+$SKIP --ignore-extras > test.out 2> test.err
+$DIFF test.expect test.out
+$DIFF test.expect.err test.err
+rm test.expect test.out
+rm test.expect.err test.err
+
+echo "> skip lines until 4 tokens seen - ignored extra tokens on same line"
+cat<<EOF > test.in
+Lorem ipsum dolor sit amet, 
+consectetur adipiscing elit, 
+sed do eiusmod tempor incididunt 
+ut labore et dolore magna aliqua. 
+Ut enim ad minim veniam, 
+quis nostrud exercitation ullamco 
+laboris nisi ut aliquip ex ea 
+commodo consequat. 
+EOF
+cat<<EOF > test.expect
+quis nostrud exercitation ullamco 
+laboris nisi ut aliquip ex ea 
+commodo consequat. 
+EOF
+$SKIP 4 test.in --token m --ignore-extras > test.out
+$DIFF test.expect test.out
+rm test.in test.expect test.out
 
 echo done