compile cmph from source

build.zig

@@ -1,6 +1,7 @@
-const Builder = @import("std").build.Builder;
+const std = @import("std");
+const zbs = std.build;
 
-pub fn build(b: *Builder) void {
+pub fn build(b: *zbs.Builder) void {
     // Standard target options allows the person running `zig build` to choose
     // what target to build for. Here we do not override the defaults, which
     // means any target is allowed, and the default is native. Other options
@@ -11,24 +12,78 @@ pub fn build(b: *Builder) void {
     // between Debug, ReleaseSafe, ReleaseFast, and ReleaseSmall.
     const mode = b.standardReleaseOptions();
 
+    const cmph = b.addStaticLibrary("cmph", null);
+    cmph.setTarget(target);
+    cmph.setBuildMode(mode);
+    cmph.linkLibC();
+    cmph.force_pic = true;
+    cmph.addCSourceFiles(&.{
+        "deps/cmph/src/bdz.c",
+        //"deps/cmph/src/bdz_gen_lookup_table.c",
+        "deps/cmph/src/bdz_ph.c",
+        //"deps/cmph/src/bm_numbers.c",
+        "deps/cmph/src/bmz8.c",
+        "deps/cmph/src/bmz.c",
+        "deps/cmph/src/brz.c",
+        "deps/cmph/src/buffer_entry.c",
+        //"deps/cmph/src/buffer_manage.c",
+        "deps/cmph/src/buffer_manager.c",
+        "deps/cmph/src/chd.c",
+        "deps/cmph/src/chd_ph.c",
+        "deps/cmph/src/chm.c",
+        //"deps/cmph/src/cmph_benchmark.c",
+        "deps/cmph/src/cmph.c",
+        "deps/cmph/src/cmph_structs.c",
+        "deps/cmph/src/compressed_rank.c",
+        "deps/cmph/src/compressed_seq.c",
+        //"deps/cmph/src/djb2_hash.c",
+        "deps/cmph/src/fch_buckets.c",
+        "deps/cmph/src/fch.c",
+        //"deps/cmph/src/fnv_hash.c",
+        "deps/cmph/src/graph.c",
+        "deps/cmph/src/hash.c",
+        //"deps/cmph/src/hashtree.c"
+        "deps/cmph/src/jenkins_hash.c",
+        "deps/cmph/src/linear_string_map.c",
+        //"deps/cmph/src/main.c",
+        "deps/cmph/src/miller_rabin.c",
+        //"deps/cmph/src/sdbm_hash.c",
+        "deps/cmph/src/select.c",
+        "deps/cmph/src/vqueue.c",
+        //"deps/cmph/src/vstack.c",
+        //"deps/cmph/src/wingetopt.c",
+    }, &.{
+        "-W",
+        "-Wno-unused-function",
+        "-fomit-frame-pointer",
+        //"-DDEBUG",
+    });
+    cmph.addIncludeDir("deps/cmph/src");
+    cmph.addIncludeDir("include/deps/cmph");
+
     const exe = b.addExecutable("init-exe", "src/main.zig");
     exe.setTarget(target);
     exe.setBuildMode(mode);
-    exe.linkLibC();
+    addCmphDeps(exe, cmph);
-    exe.linkSystemLibrary("cmph");
     exe.install();
 
     {
         const turbonss_test = b.addTest("src/main.zig");
-        turbonss_test.linkLibC();
+        addCmphDeps(turbonss_test, cmph);
-        turbonss_test.linkSystemLibrary("cmph");
         const test_step = b.step("test", "Run the tests");
         test_step.dependOn(&turbonss_test.step);
     }
 
-    const run_cmd = exe.run();
+    {
-    run_cmd.step.dependOn(b.getInstallStep());
+        const run_cmd = exe.run();
-
+        run_cmd.step.dependOn(b.getInstallStep());
-    const run_step = b.step("run", "Run the app");
+        const run_step = b.step("run", "Run the app");
-    run_step.dependOn(&run_cmd.step);
+        run_step.dependOn(&run_cmd.step);
+    }
+}
+
+fn addCmphDeps(exe: *zbs.LibExeObjStep, cmph: *zbs.LibExeObjStep) void {
+    exe.linkLibC();
+    exe.linkLibrary(cmph);
+    exe.addIncludeDir("deps/cmph/src");
 }

include/deps/cmph/config.h

@@ -0,0 +1,86 @@
+/* config.h.  Generated from config.h.in by configure.  */
+/* config.h.in.  Generated from configure.ac by autoheader.  */
+
+/* Define to 1 if you have the <dlfcn.h> header file. */
+#define HAVE_DLFCN_H 1
+
+/* Define to 1 if you have the <getopt.h> header file. */
+#define HAVE_GETOPT_H 1
+
+/* Define to 1 if you have the <hopscotch_map.h> header file. */
+/* #undef HAVE_HOPSCOTCH_MAP_H */
+
+/* Define to 1 if you have the <inttypes.h> header file. */
+#define HAVE_INTTYPES_H 1
+
+/* Define to 1 if you have the `check' library (-lcheck). */
+/* #undef HAVE_LIBCHECK */
+
+/* Define to 1 if you have the <math.h> header file. */
+#define HAVE_MATH_H 1
+
+/* Define to 1 if you have the <memory.h> header file. */
+#define HAVE_MEMORY_H 1
+
+/* Define if g++ supports C++0x features. */
+/* #undef HAVE_STDCXX_0X */
+
+/* Define to 1 if you have the <stdint.h> header file. */
+#define HAVE_STDINT_H 1
+
+/* Define to 1 if you have the <stdlib.h> header file. */
+#define HAVE_STDLIB_H 1
+
+/* Define to 1 if you have the <strings.h> header file. */
+#define HAVE_STRINGS_H 1
+
+/* Define to 1 if you have the <string.h> header file. */
+#define HAVE_STRING_H 1
+
+/* Define to 1 if you have the <sys/stat.h> header file. */
+#define HAVE_SYS_STAT_H 1
+
+/* Define to 1 if you have the <sys/types.h> header file. */
+#define HAVE_SYS_TYPES_H 1
+
+/* Define to 1 if you have the <unistd.h> header file. */
+#define HAVE_UNISTD_H 1
+
+/* Define to the sub-directory where libtool stores uninstalled libraries. */
+#define LT_OBJDIR ".libs/"
+
+/* Name of package */
+#define PACKAGE "cmph"
+
+/* Define to the address where bug reports for this package should be sent. */
+#define PACKAGE_BUGREPORT ""
+
+/* Define to the full name of this package. */
+#define PACKAGE_NAME "cmph"
+
+/* Define to the full name and version of this package. */
+#define PACKAGE_STRING "cmph 2.0.2"
+
+/* Define to the one symbol short name of this package. */
+#define PACKAGE_TARNAME "cmph"
+
+/* Define to the home page for this package. */
+#define PACKAGE_URL ""
+
+/* Define to the version of this package. */
+#define PACKAGE_VERSION "2.0.2"
+
+/* Define to 1 if you have the ANSI C header files. */
+#define STDC_HEADERS 1
+
+/* Version number of package */
+#define VERSION "2.0.2"
+
+/* Number of bits in a file offset, on hosts where this is settable. */
+/* #undef _FILE_OFFSET_BITS */
+
+/* Define to make fseeko etc. visible, on some hosts. */
+/* #undef _LARGEFILE_SOURCE */
+
+/* Define for large files, on AIX-style hosts. */
+/* #undef _LARGE_FILES */

src/main.zig

@@ -1,35 +1,15 @@
 const std = @import("std");
-const ArrayList = std.ArrayList;
 
 const c = @cImport({
     @cDefine("DEBUG", "1");
     @cInclude("stdio.h");
+    @cInclude("string.h");
     @cInclude("cmph.h");
 });
 
 const tempMph = "temp.mph";
 
-pub fn main() !void {
+pub fn main() !void {}
-
-    //    var hash: ?*c.cmph_t = c.cmph_new(config);
-    //    c.cmph_config_destroy(config);
-    //    _ = c.cmph_dump(hash, mphf_fd);
-    //    c.cmph_destroy(hash);
-    //    _ = c.fclose(mphf_fd);
-    //    mphf_fd = c.fopen("temp.mph", "r");
-    //    hash = c.cmph_load(mphf_fd);
-    //    while (i < nkeys) {
-    //        var key: [*c]const u8 = vector[i];
-    //        var id: c_uint = c.cmph_search(hash, key, @bitCast(c.cmph_uint32, @truncate(c_uint, 10)));
-    //        try stdout.print("key:{s} -- hash:{u}\n", key, id);
-    //        i +%= 1;
-    //    }
-    //    c.cmph_destroy(hash);
-    //    c.cmph_io_vector_adapter_destroy(source);
-    //    _ = c.fclose(mphf_fd);
-    //    return 0;
-    //}
-}
 
 test "simple cmph usage" {
     var arena_instance = std.heap.ArenaAllocator.init(std.heap.page_allocator);
@@ -38,28 +18,26 @@ test "simple cmph usage" {
     const stderr = std.io.getStdErr().writer();
 
     _ = stdout;
-    var vector = ArrayList([*:0]const u8).init(arena);
+    var vector = std.ArrayList([*:0]const u8).init(arena);
-    try vector.append("aaaaaaaaaa");
+    try vector.appendSlice(&.{
-    try vector.append("bbbbbbbbbb");
+        "aaaaaaaaaa",
-    try vector.append("cccccccccc");
+        "bbbbbbbbbb",
-    try vector.append("dddddddddd");
+        "cccccccccc",
-    try vector.append("eeeeeeeeee");
+        "dddddddddd",
-    try vector.append("ffffffffff");
+        "eeeeeeeeee",
-    try vector.append("gggggggggg");
+        "ffffffffff",
-    try vector.append("hhhhhhhhhh");
+        "gggggggggg",
-    try vector.append("iiiiiiiiii");
+        "hhhhhhhhhh",
-    try vector.append("jjjjjjjjjj");
+        "iiiiiiiiii",
+        "jjjjjjjjjj",
+    });
+    var vector2 = try vector.clone();
+    var nkeys = @truncate(c_uint, vector.items.len);
 
-    var mphf_fh = try std.fs.cwd().createFile(tempMph, .{});
+    var mphf_fd = c.fopen(tempMph, "w");
-    defer {
-        std.fs.cwd().deleteFile(tempMph) catch |err| {
-            stderr.print("error removing file: {s}\n", .{@errorName(err)}) catch {};
-        };
-    }
-    var mphf_fd = c.fdopen(mphf_fh.handle, "w");
-    var vector_len = @truncate(c_uint, vector.items.len);
     var cvector = @ptrCast([*c][*c]u8, vector.toOwnedSlice().ptr);
-    var source = c.cmph_io_vector_adapter(cvector, vector_len);
+    var source = c.cmph_io_vector_adapter(cvector, nkeys);
+    defer c.cmph_io_vector_adapter_destroy(source);
     var config: *c.cmph_config_t = c.cmph_config_new(source) orelse return error.OutOfMemory;
     c.cmph_config_set_algo(config, c.CMPH_BRZ);
     c.cmph_config_set_mphf_fd(config, mphf_fd);
@@ -67,11 +45,10 @@ test "simple cmph usage" {
     c.cmph_config_destroy(config);
     _ = c.cmph_dump(hash, mphf_fd);
     c.cmph_destroy(hash);
-    mphf_fh.close();
+    try closeCFile(mphf_fd);
 
-    mphf_fh = try std.fs.cwd().openFile(tempMph, .{ .mode = .read_only });
+    mphf_fd = c.fopen(tempMph, "r");
-    mphf_fd = c.fdopen(mphf_fh.handle, "r");
+    defer _ = c.fclose(mphf_fd);
-    defer mphf_fh.close();
 
     var got_hash: ?*c.cmph_t = c.cmph_load(mphf_fd);
     if (got_hash) |real_hash| {
@@ -79,6 +56,20 @@ test "simple cmph usage" {
     } else {
         try stderr.print("failed to unwrap hash\n", .{});
     }
+    defer c.cmph_destroy(hash);
+
+    try stderr.print("\n", .{});
+    for (vector2.items) |key| {
+        var id = c.cmph_search(hash, key, @truncate(c_uint, c.strlen(key)));
+        try stderr.print("key: {s}, id: {d}\n", .{ key, id });
+    }
+}
+
+fn closeCFile(f: *c.FILE) !void {
+    var close_code = c.fclose(f);
+    if (close_code != 0) {
+        return std.os.unexpectedErrno(std.os.errno(close_code));
+    }
 }
 
 const expectEqual = std.testing.expectEqual;
@@ -87,7 +78,7 @@ test "char**" {
     var arena_instance = std.heap.ArenaAllocator.init(std.heap.page_allocator);
     const arena = arena_instance.allocator();
 
-    var arrl = ArrayList([*:0]const u8).init(arena);
+    var arrl = std.ArrayList([*:0]const u8).init(arena);
     try arrl.append("foo");
     try arrl.append("bar");