Add zh-CN option in language dropdown

add zh-CN translation

.drone.yml

@@ -11,21 +11,6 @@ steps:
     image: simon987/sist2-build
     commands:
       - ./scripts/build.sh
-  - name: docker
-    image: plugins/docker
-    settings:
-      username:
-        from_secret: DOCKER_USER
-      password:
-        from_secret: DOCKER_PASSWORD
-      repo: simon987/sist2
-      context: ./
-      dockerfile: ./Dockerfile
-      auto_tag: true
-      auto_tag_suffix: x64-linux
-      when:
-        event:
-          - tag
   - name: scp files
     image: appleboy/drone-scp
     settings:
@@ -42,6 +27,21 @@ steps:
         - ./VERSION
         - ./sist2-x64-linux
         - ./sist2-x64-linux-debug
+  - name: docker
+    image: plugins/docker
+    settings:
+      username:
+        from_secret: DOCKER_USER
+      password:
+        from_secret: DOCKER_PASSWORD
+      repo: simon987/sist2
+      context: ./
+      dockerfile: ./Dockerfile
+      auto_tag: true
+      auto_tag_suffix: x64-linux
+      when:
+        event:
+          - tag
 
 ---
 kind: pipeline

.gitmodules

@@ -1,6 +1,3 @@
-[submodule "third-party/libscan"]
-	path = third-party/libscan
-	url = https://github.com/simon987/libscan
 [submodule "third-party/argparse"]
 	path = third-party/argparse
 	url = https://github.com/simon987/argparse

CMakeLists.txt

@@ -22,9 +22,6 @@ add_subdirectory(third-party/argparse)
 
 add_executable(sist2
 
-        # argparse
-        third-party/argparse/argparse.h third-party/argparse/argparse.c
-
         src/main.c
         src/sist.h
         src/io/walk.h src/io/walk.c
@@ -41,7 +38,11 @@ add_executable(sist2
         src/log.c src/log.h
         src/cli.c src/cli.h
         src/stats.c src/stats.h src/ctx.c
-        src/parsing/sidecar.c src/parsing/sidecar.h)
+        src/parsing/sidecar.c src/parsing/sidecar.h
+
+        # argparse
+        third-party/argparse/argparse.h third-party/argparse/argparse.c
+        )
 
 target_link_directories(sist2 PRIVATE BEFORE ${_VCPKG_INSTALLED_DIR}/${VCPKG_TARGET_TRIPLET}/lib/)
 set(CMAKE_FIND_LIBRARY_SUFFIXES .a .lib)
@@ -86,6 +87,7 @@ if (SIST_DEBUG)
             sist2
             PRIVATE
             -fsanitize=address
+            -static-libasan
     )
     set_target_properties(
             sist2

README.md

@@ -51,7 +51,7 @@ sist2 (Simple incremental search tool)
     1. Download the [latest sist2 release](https://github.com/simon987/sist2/releases) *
     1. *(or)* Download a [development snapshot](https://files.simon987.net/.gate/sist2/simon987_sist2/) *(Not
        recommended!)*
-    1. *(or)* `docker pull simon987/sist2:2.11.4-x64-linux`
+    1. *(or)* `docker pull simon987/sist2:2.11.6-x64-linux`
 
 1. See [Usage guide](docs/USAGE.md)
 
@@ -143,7 +143,7 @@ docker run --rm my-sist2-image cat /root/sist2 > sist2-x64-linux
 
     ```bash
     vcpkg install curl[core,openssl]
-    vcpkg install lmdb cjson glib brotli libarchive[core,bzip2,libxml2,lz4,lzma,lzo] pthread tesseract libxml2 libmupdf gtest mongoose libuuid libmagic libraw jasper lcms gumbo
+    vcpkg install lmdb cjson glib brotli libarchive[core,bzip2,libxml2,lz4,lzma,lzo] pthread tesseract libxml2 libmupdf gtest mongoose libmagic libraw jasper lcms gumbo
     ```
 
 1. Build

docs/USAGE.md

@@ -85,7 +85,7 @@ Exec-script options
 ### Scan options
 
 * `-t, --threads` 
-      Number of threads for file parsing. **Do not set a number higher than `$(nproc)` or `$(Get-WmiObject Win32_ComputerSystem).NumberOfLogicalProcessors` in Windows!**
+      Number of threads for file parsing. **Do not set a number higher than `$(nproc)` or `$(Get-CimInstance Win32_ComputerSystem).NumberOfLogicalProcessors` in Windows!**
 * `-q, --quality` 
     Thumbnail quality, on a scale of 1.0 to 31.0, 1.0 being the best.
 * `--size` 

sist2-vue/src/components/IndexPicker.vue

@@ -133,6 +133,11 @@ export default Vue.extend({
   font-size: 80%;
 }
 
+.theme-black .version-badge {
+  color: #eee !important;
+  background: none;
+}
+
 .version-badge {
   color: #222 !important;
   background: none;

sist2-vue/src/i18n/messages.ts

@@ -72,7 +72,8 @@ export default {
         },
         lang: {
             en: "English",
-            fr: "Français"
+            fr: "Français",
+            "zh-CN": "简体中文",
         },
         displayMode: {
             grid: "Grid",
@@ -228,7 +229,8 @@ export default {
         },
         lang: {
             en: "English",
-            fr: "Français"
+            fr: "Français",
+            "zh-CN": "简体中文",
         },
         displayMode: {
             grid: "Grille",
@@ -311,5 +313,161 @@ export default {
             selectedIndex: "indice sélectionné",
             selectedIndices: "indices sélectionnés",
         },
-    }
+    },
+    "zh-CN": {
+        searchBar: {
+            simple: "搜索",
+            advanced: "高级搜索",
+            fuzzy: "模糊搜索"
+        },
+        download: "下载",
+        and: "与",
+        page: "页",
+        pages: "页",
+        mimeTypes: "文件类型",
+        tags: "标签",
+        help: {
+            simpleSearch: "简易搜索",
+            advancedSearch: "高级搜索",
+            help: "帮助",
+            term: "<关键词>",
+            and: "与操作",
+            or: "或操作",
+            not: "反选单个关键词",
+            quotes: "括起来的部分视为一个关键词，保序",
+            prefix: "在词尾使用时，匹配前缀",
+            parens: "表达式编组",
+            tildeTerm: "匹配编辑距离以内的关键词",
+            tildePhrase: "匹配短语，容忍一些非匹配词",
+            example1:
+                "例如: <code>\"番茄\" +(炒蛋 | 牛腩) -饭</code> 将匹配" +
+                "短语 <i>番茄炒蛋</i>、<i>炒蛋</i> 或者 <i>牛腩</i>，而忽略任何带有" +
+                "<i>饭</i>的关键词.",
+            defaultOperator:
+                "表达式中无<code>+</code>或者<code>|</code>时，默认使用" +
+                "<code>+</code>（与操作）。",
+            fuzzy:
+                "选中<b>模糊搜索</b>选项时，返回部分匹配的结果（3-grams)。",
+            moreInfoSimple: "详细信息：<a target=\"_blank\" " +
+                "rel=\"noreferrer\" href=\"//www.elastic.co/guide/en/elasticsearch/reference/current/query-dsl-simple-query-string-query.html\">Elasticsearch文档</a>",
+            moreInfoAdvanced: "高级搜索模式文档：<a target=\"_blank\" rel=\"noreferrer\" href=\"//www.elastic.co/guide/en/elasticsearch/reference/current/query-dsl-query-string-query.html#query-string-syntax\">Elasticsearch文档</a>"
+        },
+        config: "配置",
+        configDescription: "配置在此浏览器中实时保存。",
+        configReset: "重置所有设置",
+        searchOptions: "搜索选项",
+        treemapOptions: "树状图选项",
+        displayOptions: "显示选项",
+        opt: {
+            lang: "语言",
+            highlight: "启用高亮",
+            fuzzy: "默认使用模糊搜索",
+            searchInPath: "匹配文档路径",
+            suggestPath: "搜索框启用自动补全",
+            fragmentSize: "高亮上下文大小",
+            queryMode: "搜索模式",
+            displayMode: "显示",
+            columns: "列数",
+            treemapType: "树状图类属性",
+            treemapTiling: "树状图平铺",
+            treemapColorGroupingDepth: "树状图颜色编组深度（展开）",
+            treemapColor: "树状图颜色（折叠）",
+            treemapSize: "树状图大小",
+            theme: "主题",
+            lightboxLoadOnlyCurrent: "在图片查看器中，不要预读相邻的全图",
+            slideDuration: "幻灯片时长",
+            resultSize: "每页结果数",
+            tagOrOperator: "使用或操作（OR）匹配多个标签。",
+            hideDuplicates: "使用校验码隐藏重复结果",
+            hideLegacy: "隐藏'legacyES' Elasticsearch 通知"
+        },
+        queryMode: {
+            simple: "简单",
+            advanced: "高级",
+        },
+        lang: {
+            en: "English",
+            fr: "Français",
+            "zh-CN": "简体中文",
+        },
+        displayMode: {
+            grid: "网格",
+            list: "列表",
+        },
+        columns: {
+            auto: "自动"
+        },
+        treemapType: {
+            cascaded: "折叠",
+            flat: "平铺（紧凑）"
+        },
+        treemapSize: {
+            small: "小",
+            medium: "中",
+            large: "大",
+            xLarge: "加大",
+            xxLarge: "加加大",
+            custom: "自订",
+        },
+        treemapTiling: {
+            binary: "Binary",
+            squarify: "Squarify",
+            slice: "Slice",
+            dice: "Dice",
+            sliceDice: "Slice & Dice",
+        },
+        theme: {
+            light: "亮",
+            black: "暗"
+        },
+        hit: "命中",
+        hits: "命中",
+        details: "详细信息",
+        stats: "统计信息",
+        queryTime: "查询时间",
+        totalSize: "总大小",
+        pathBar: {
+            placeholder: "过滤路径",
+            modalTitle: "选择路径"
+        },
+        debug: "调试信息",
+        debugDescription: "对调试除错有用的信息。 若您遇到bug或者想建议新功能，请提交新Issue到" +
+            "<a href='https://github.com/simon987/sist2/issues/new/choose'>这里</a>.",
+        tagline: "标签栏",
+        toast: {
+            esConnErrTitle: "Elasticsearch连接错误",
+            esConnErr: "sist2 web 模块连接Elasticsearch出错。" +
+                "查看服务日志以获取更多信息。",
+            esQueryErrTitle: "查询错误",
+            esQueryErr: "无法识别或执行查询，请查阅高级搜索文档。" +
+                "查看服务日志以获取更多信息。",
+            dupeTagTitle: "重复标签",
+            dupeTag: "该标签已存在于此文档。"
+        },
+        saveTagModalTitle: "增加标签",
+        saveTagPlaceholder: "标签名",
+        confirm: "确认",
+        sort: {
+            relevance: "相关度",
+            dateAsc: "日期（由旧到新）",
+            dateDesc: "日期（由新到旧）",
+            sizeAsc: "大小（从小到大）",
+            sizeDesc: "大小（从大到小）",
+            nameAsc: "名字（A-z）",
+            nameDesc: "名字 （Z-a）",
+            random: "随机",
+        },
+        d3: {
+            mimeCount: "各类文件数量分布",
+            mimeSize: "各类文件大小分布",
+            dateHistogram: "文件修改时间分布",
+            sizeHistogram: "文件大小分布",
+        },
+        indexPicker: {
+            selectNone: "清空",
+            selectAll: "全选",
+            selectedIndex: "选中索引",
+            selectedIndices: "选中索引",
+        },
+    },
 }

sist2-vue/src/views/Configuration.vue

@@ -133,6 +133,7 @@ export default {
       langOptions: [
         {value: "en", text: this.$t("lang.en")},
         {value: "fr", text: this.$t("lang.fr")},
+        {value: "zh-CN", text: this.$t("lang.zh-CN")},
       ],
       queryModeOptions: [
         {value: "simple", text: this.$t("queryMode.simple")},

src/cli.c

@@ -22,6 +22,7 @@
 const char *TESS_DATAPATHS[] = {
         "/usr/share/tessdata/",
         "/usr/share/tesseract-ocr/tessdata/",
+        "/usr/share/tesseract-ocr/4.00/tessdata/",
         "./",
         NULL
 };
@@ -218,6 +219,19 @@ int scan_args_validate(scan_args_t *args, int argc, const char **argv) {
         args->max_memory_buffer = DEFAULT_MAX_MEM_BUFFER;
     }
 
+    if (args->list_path != NULL) {
+        if(strcmp(args->list_path, "-") == 0) {
+            args->list_file = stdin;
+            LOG_DEBUG("cli.c", "Using stdin as list file")
+        } else {
+            args->list_file = fopen(args->list_path, "r");
+
+            if (args->list_file == NULL) {
+                LOG_FATALF("main.c", "List file could not be opened: %s (%s)", args->list_path, errno);
+            }
+        }
+    }
+
     LOG_DEBUGF("cli.c", "arg quality=%f", args->quality)
     LOG_DEBUGF("cli.c", "arg size=%d", args->size)
     LOG_DEBUGF("cli.c", "arg content_size=%d", args->content_size)
@@ -237,6 +251,7 @@ int scan_args_validate(scan_args_t *args, int argc, const char **argv) {
     LOG_DEBUGF("cli.c", "arg fast_epub=%d", args->fast_epub)
     LOG_DEBUGF("cli.c", "arg treemap_threshold=%f", args->treemap_threshold)
     LOG_DEBUGF("cli.c", "arg max_memory_buffer=%d", args->max_memory_buffer)
+    LOG_DEBUGF("cli.c", "arg list_path=%s", args->list_path)
 
     return 0;
 }

src/cli.h

@@ -29,6 +29,8 @@ typedef struct scan_args {
     int read_subtitles;
     int fast_epub;
     int calculate_checksums;
+    char *list_path;
+    FILE *list_file;
 } scan_args_t;
 
 scan_args_t *scan_args_create();

src/ctx.h

@@ -41,6 +41,7 @@ typedef struct {
 
     GHashTable *original_table;
     GHashTable *copy_table;
+    pthread_mutex_t copy_table_mu;
 
     pcre *exclude;
     pcre_extra *exclude_extra;

src/io/walk.c

@@ -4,6 +4,8 @@
 
 #include <ftw.h>
 
+#define STR_STARTS_WITH(x, y) (strncmp(y, x, strlen(y) - 1) == 0)
+
 __always_inline
 parse_job_t *create_fs_parse_job(const char *filepath, const struct stat *info, int base) {
     int len = (int) strlen(filepath);
@@ -57,10 +59,11 @@ int handle_entry(const char *filepath, const struct stat *info, int typeflag, st
             pthread_mutex_lock(&ScanCtx.dbg_file_counts_mu);
             ScanCtx.dbg_excluded_files_count += 1;
             pthread_mutex_unlock(&ScanCtx.dbg_file_counts_mu);
-            return 0;
         } else if (typeflag == FTW_D) {
             return FTW_SKIP_SUBTREE;
         }
+
+        return FTW_CONTINUE;
     }
 
     if (typeflag == FTW_F && S_ISREG(info->st_mode)) {
@@ -76,3 +79,57 @@ int handle_entry(const char *filepath, const struct stat *info, int typeflag, st
 int walk_directory_tree(const char *dirpath) {
     return nftw(dirpath, handle_entry, MAX_FILE_DESCRIPTORS, FTW_PHYS | FTW_ACTIONRETVAL);
 }
+
+int iterate_file_list(void *input_file) {
+
+    char buf[PATH_MAX];
+    struct stat info;
+
+    while (fgets(buf, sizeof(buf), input_file) != NULL) {
+
+        // Remove trailing newline
+        *(buf + strlen(buf) - 1) = '\0';
+
+        int stat_ret = stat(buf, &info);
+
+        if (stat_ret != 0) {
+            LOG_ERRORF("walk.c", "Could not stat file %s (%s)", buf, strerror(errno));
+            continue;
+        }
+
+        if (!S_ISREG(info.st_mode)) {
+            LOG_ERRORF("walk.c", "Is not a regular file: %s", buf);
+            continue;
+        }
+
+        char *absolute_path = canonicalize_file_name(buf);
+
+        if (absolute_path == NULL) {
+            LOG_FATALF("walk.c", "FIXME: Could not get absolute path of %s", buf);
+        }
+
+        if (ScanCtx.exclude != NULL && EXCLUDED(absolute_path)) {
+            LOG_DEBUGF("walk.c", "Excluded: %s", absolute_path)
+
+            if (S_ISREG(info.st_mode)) {
+                pthread_mutex_lock(&ScanCtx.dbg_file_counts_mu);
+                ScanCtx.dbg_excluded_files_count += 1;
+                pthread_mutex_unlock(&ScanCtx.dbg_file_counts_mu);
+            }
+
+            continue;
+        }
+
+        if (!STR_STARTS_WITH(absolute_path, ScanCtx.index.desc.root)) {
+            LOG_FATALF("walk.c", "File is not a children of root folder (%s): %s", ScanCtx.index.desc.root, buf);
+        }
+
+        int base = (int) (strrchr(buf, '/') - buf) + 1;
+
+        parse_job_t *job = create_fs_parse_job(absolute_path, &info, base);
+        free(absolute_path);
+        tpool_add_work(ScanCtx.pool, parse, job);
+    }
+
+    return 0;
+}

src/io/walk.h

@@ -5,4 +5,6 @@
 
 int walk_directory_tree(const char *);
 
+int iterate_file_list(void* input_file);
+
 #endif

src/main.c

@@ -14,6 +14,9 @@
 #include "parsing/mime.h"
 #include "parsing/parse.h"
 
+#include <signal.h>
+#include <unistd.h>
+
 #include "stats.h"
 
 #define DESCRIPTION "Lightning-fast file system indexer and search tool."
@@ -29,8 +32,6 @@ static const char *const usage[] = {
         NULL,
 };
 
-#include<signal.h>
-#include<unistd.h>
 
 static __sighandler_t sigsegv_handler = NULL;
 static __sighandler_t sigabrt_handler = NULL;
@@ -169,6 +170,7 @@ void initialize_scan_context(scan_args_t *args) {
     ScanCtx.dbg_current_files = g_hash_table_new_full(g_int64_hash, g_int64_equal, NULL, NULL);
     pthread_mutex_init(&ScanCtx.dbg_current_files_mu, NULL);
     pthread_mutex_init(&ScanCtx.dbg_file_counts_mu, NULL);
+    pthread_mutex_init(&ScanCtx.copy_table_mu, NULL);
 
     ScanCtx.calculate_checksums = args->calculate_checksums;
 
@@ -334,10 +336,20 @@ void sist2_scan(scan_args_t *args) {
     ScanCtx.writer_pool = tpool_create(1, writer_cleanup, TRUE, FALSE);
     tpool_start(ScanCtx.writer_pool);
 
+    if (args->list_path) {
+        // Scan using file list
+        int list_ret = iterate_file_list(args->list_file);
+        if (list_ret != 0) {
+            LOG_FATALF("main.c", "iterate_file_list() failed! (%d)", list_ret)
+        }
+    } else {
+        // Scan directory recursively
         int walk_ret = walk_directory_tree(ScanCtx.index.desc.root);
         if (walk_ret == -1) {
             LOG_FATALF("main.c", "walk_directory_tree() failed! %s (%d)", strerror(errno), errno)
         }
+    }
+
     tpool_wait(ScanCtx.pool);
     tpool_destroy(ScanCtx.pool);
 
@@ -577,6 +589,9 @@ int main(int argc, const char *argv[]) {
             OPT_BOOLEAN(0, "fast-epub", &scan_args->fast_epub,
                         "Faster but less accurate EPUB parsing (no thumbnails, metadata)"),
             OPT_BOOLEAN(0, "checksums", &scan_args->calculate_checksums, "Calculate file checksums when scanning."),
+            OPT_STRING(0, "list-file", &scan_args->list_path, "Specify a list of newline-delimited paths to be scanned"
+                                                              " instead of normal directory traversal. Use '-' to read"
+                                                              " from stdin."),
 
             OPT_GROUP("Index options"),
             OPT_INTEGER('t', "threads", &common_threads, "Number of threads. DEFAULT=1"),

src/parsing/parse.c

@@ -79,7 +79,9 @@ void parse(void *arg) {
 
     int inc_ts = incremental_get(ScanCtx.original_table, doc->path_md5);
     if (inc_ts != 0 && inc_ts == job->vfile.info.st_mtim.tv_sec) {
+        pthread_mutex_lock(&ScanCtx.copy_table_mu);
         incremental_mark_file_for_copy(ScanCtx.copy_table, doc->path_md5);
+        pthread_mutex_unlock(&ScanCtx.copy_table_mu);
 
         pthread_mutex_lock(&ScanCtx.dbg_file_counts_mu);
         ScanCtx.dbg_skipped_files_count += 1;

src/sist.h

@@ -53,7 +53,7 @@
 #include <ctype.h>
 #include "git_hash.h"
 
-#define VERSION "2.11.5"
+#define VERSION "2.11.6"
 static const char *const Version = VERSION;
 
 #ifndef SIST_PLATFORM

src/util.h

@@ -133,6 +133,9 @@ static int incremental_get_str(GHashTable *table, const char *path_md5) {
     }
 }
 
+/**
+ * Not thread safe!
+ */
 __always_inline
 static int incremental_mark_file_for_copy(GHashTable *table, const unsigned char path_md5[MD5_DIGEST_LENGTH]) {
     char *ptr = malloc(MD5_STR_LENGTH);

third-party/libscan/libscan/ooxml/ooxml.c

@@ -15,18 +15,18 @@ static int should_read_part(const char *part) {
     }
 
     if (    // Word
-            STR_STARTS_WITH(part, "word/document.xml")
-            || STR_STARTS_WITH(part, "word/footnotes.xml")
-            || STR_STARTS_WITH(part, "word/endnotes.xml")
-            || STR_STARTS_WITH(part, "word/footer")
-            || STR_STARTS_WITH(part, "word/header")
+            STR_STARTS_WITH_CONSTANT(part, "word/document.xml")
+            || STR_STARTS_WITH_CONSTANT(part, "word/footnotes.xml")
+            || STR_STARTS_WITH_CONSTANT(part, "word/endnotes.xml")
+            || STR_STARTS_WITH_CONSTANT(part, "word/footer")
+            || STR_STARTS_WITH_CONSTANT(part, "word/header")
             // PowerPoint
-            || STR_STARTS_WITH(part, "ppt/slides/slide")
-            || STR_STARTS_WITH(part, "ppt/notesSlides/slide")
+            || STR_STARTS_WITH_CONSTANT(part, "ppt/slides/slide")
+            || STR_STARTS_WITH_CONSTANT(part, "ppt/notesSlides/slide")
             // Excel
-            || STR_STARTS_WITH(part, "xl/worksheets/sheet")
-            || STR_STARTS_WITH(part, "xl/sharedStrings.xml")
-            || STR_STARTS_WITH(part, "xl/workbook.xml")
+            || STR_STARTS_WITH_CONSTANT(part, "xl/worksheets/sheet")
+            || STR_STARTS_WITH_CONSTANT(part, "xl/sharedStrings.xml")
+            || STR_STARTS_WITH_CONSTANT(part, "xl/workbook.xml")
             ) {
         return TRUE;
     }

third-party/libscan/libscan/raw/raw.c

@@ -143,7 +143,7 @@ void parse_raw(scan_raw_ctx_t *ctx, vfile_t *f, document_t *doc) {
 
     libraw_gps_info_t gps = libraw_lib->other.parsed_gps;
     double gps_longitude_dec =
-            (gps.longtitude[0] + gps.longtitude[1] / 60 + gps.longtitude[2] / 3600) * DMS_REF(gps.longref);
+            (gps.longitude[0] + gps.longitude[1] / 60 + gps.longitude[2] / 3600) * DMS_REF(gps.longref);
     snprintf(tmp, sizeof(tmp), "%.15f", gps_longitude_dec);
     if (gps_longitude_dec != 0.0) {
         APPEND_STR_META(doc, MetaExifGpsLongitudeDec, tmp)
@@ -163,7 +163,13 @@ void parse_raw(scan_raw_ctx_t *ctx, vfile_t *f, document_t *doc) {
         return;
     }
 
-    libraw_unpack_thumb(libraw_lib);
+    int unpack_ret = libraw_unpack_thumb(libraw_lib);
+    if (unpack_ret != 0) {
+        CTX_LOG_ERRORF(f->filepath, "libraw_unpack_thumb returned error code %d", unpack_ret)
+        free(buf);
+        libraw_close(libraw_lib);
+        return;
+    }
 
     int errc = 0;
     libraw_processed_image_t *thumb = libraw_dcraw_make_mem_thumb(libraw_lib, &errc);

third-party/libscan/libscan/util.h

@@ -7,7 +7,7 @@
 #include "../third-party/utf8.h/utf8.h"
 #include "macros.h"
 
-#define STR_STARTS_WITH(x, y) (strncmp(y, x, sizeof(y) - 1) == 0)
+#define STR_STARTS_WITH_CONSTANT(x, y) (strncmp(y, x, sizeof(y) - 1) == 0)
 
 #define TEXT_BUF_FULL (-1)
 #define INITIAL_BUF_SIZE (1024 * 16)

third-party/libscan/test/main.cpp

@@ -227,7 +227,7 @@ TEST(Ebook, Utf8Pdf) {
 
     parse_ebook(&ebook_500_ctx, &f, "application/pdf", &doc);
 
-    ASSERT_TRUE(STR_STARTS_WITH(get_meta(&doc, MetaContent)->str_val, "最後測試 "));
+    ASSERT_TRUE(STR_STARTS_WITH_CONSTANT(get_meta(&doc, MetaContent)->str_val, "最後測試 "));
     cleanup(&doc, &f);
 }
 
@@ -245,7 +245,7 @@ TEST(Ebook, Utf8PdfInvalidChars) {
     // It should say "HART is a group of highly qualified ..." but the PDF
     //  text is been intentionally fucked with by the authors
     // We can at least filter out the non-printable/invalid characters like '<27>' etc
-    ASSERT_TRUE(STR_STARTS_WITH(get_meta(&doc, MetaContent)->str_val, "HART i a g f highl alified "));
+    ASSERT_TRUE(STR_STARTS_WITH_CONSTANT(get_meta(&doc, MetaContent)->str_val, "HART i a g f highl alified "));
     cleanup(&doc, &f);
 }
 
@@ -780,6 +780,19 @@ TEST(Arc, EncryptedZip) {
 }
 
 /* RAW */
+TEST(RAW, Segfault1) {
+    vfile_t f;
+    document_t doc;
+    load_doc_file("libscan-test-files/test_files/raw/segfault1.dng", &f, &doc);
+
+    parse_raw(&raw_ctx, &f, &doc);
+
+    ASSERT_EQ(get_meta(&doc, MetaWidth)->long_val, 3840);
+    ASSERT_EQ(get_meta(&doc, MetaHeight)->long_val, 7680);
+
+    cleanup(&doc, &f);
+}
+
 TEST(RAW, Panasonic) {
     vfile_t f;
     document_t doc;