I guess it was localhost this time

* Add Vazir Font

* Add Vazir Font License

* fix prettier problem

* Shabnam added

.circleci/images/plume-buildenv/Caddyfile

@@ -1,5 +1,5 @@
 localhost:443 {
-  proxy / localhost:7878 {
+  proxy / integration:7878 {
     transparent
   }
   tls self_signed

.drone.jsonnet

@@ -0,0 +1,233 @@
+// This is the CI config for Plume.
+// It uses a Drone CI instance, on https://ci.joinplu.me
+
+// First of all, we define a few useful constants
+
+// This Docker image contains everything we need to build Plume.
+// Its Dockerfile can be found at https://git.joinplu.me/plume/buildenv
+local plumeEnv = "plumeorg/plume-buildenv:v0.2.0";
+
+// Common cache config
+local cacheConfig(name, extra) = {
+    name: name,
+    image: "meltwater/drone-cache:dev",
+    pull: true,
+    environment: {
+      AWS_ACCESS_KEY_ID: { from_secret: 'minio_key' },
+      AWS_SECRET_ACCESS_KEY: { from_secret: 'minio_secret' },
+    },
+    settings: extra + {
+        cache_key: 'v0-{{ checksum "Cargo.lock" }}-{{ .Commit.Branch }}',
+        archive_format: "gzip",
+        mount: [ "~/.cargo/", "./target" ],
+        bucket: 'cache',
+        path_style: true,
+        endpoints: "127.0.0.1:9000",
+        region: 'us-east-1',
+        debug: true,
+    },
+    volumes: [ { name: "cache", path: "/tmp/cache" } ]
+};
+
+
+// A pipeline step that restores the cache.
+// The cache contains all the cargo build files.
+// Thus, we don't have to download and compile all of our dependencies for each
+// commit.
+// This cache is only "deleted" when the contents of Cargo.lock changes.
+//
+// We use this plugin for caching: https://github.com/meltwater/drone-cache/
+//
+// Potential TODO: use one cache per pipeline, as we used to do when we were
+// using CircleCI.
+local restoreCache = cacheConfig("restore-cache", { restore: true });
+// And a step that saves the cache.
+local saveCache = cacheConfig("save-cache", { rebuild: true });
+
+// This step starts a PostgreSQL database if the db parameter is "postgres",
+// otherwise it does nothing.
+local startDb(db) = if db == "postgres" then {
+    name: "start-db",
+    image: "postgres:12.3-alpine",
+    detach: true,
+    environment: {
+        POSTGRES_USER: "plume",
+        POSTGRES_DB: "plume",
+        POSTGRES_PASSWORD: "password",
+    }
+} else {};
+
+// A utility function to generate a new pipeline
+local basePipeline(name, steps) = {
+    kind: "pipeline",
+    name: name,
+    type: "docker",
+    environment: {
+        RUST_TEST_THREADS: '1',
+    },
+    steps: steps
+};
+
+// And this function creates a pipeline with caching
+local cachedPipeline(name, commands) = basePipeline(
+    name,
+    [
+        restoreCache,
+        {
+            name: name,
+            image: plumeEnv,
+            commands: commands,
+        },
+        saveCache
+    ]
+);
+
+// This function creates a step to upload artifacts to Minio
+local upload(name, source) = {
+    name: name,
+    image: 'plugins/s3',
+    settings: {
+        bucket: 'artifacts',
+        source: source,
+        target: '/${DRONE_BUILD_NUMBER}',
+        path_style: true,
+        endpoint: 'http://127.0.0.1:9000',
+        access_key: { from_secret: 'minio_key' },
+        secret_key: { from_secret: 'minio_secret' },
+    },
+};
+
+
+// Here starts the actual list of pipelines!
+
+// PIPELINE 1: a pipeline that runs cargo fmt, and that fails if the style of
+// the code is not standard.
+local CargoFmt() = cachedPipeline(
+    "cargo-fmt",
+    [ "cargo fmt --all -- --check" ]
+);
+
+// PIPELINE 2: runs clippy, a tool that helps
+// you writing idiomatic Rust.
+
+// Helper function:
+local cmd(db, pkg, features=true) = if features then
+    "cargo clippy --no-default-features --features " + db + " --release -p "
+    + pkg + " -- -D warnings"
+else
+    "cargo clippy --no-default-features --release -p "
+    + pkg + " -- -D warnings";
+
+// The actual pipeline:
+local Clippy(db) = cachedPipeline(
+    "clippy-" + db,
+    [
+        cmd(db, "plume"),
+        cmd(db, "plume-cli"),
+        cmd(db, "plume-front", false)
+    ]
+);
+
+// PIPELINE 3: runs unit tests
+local Unit(db) = cachedPipeline(
+    "unit-" + db,
+    [
+        "cargo test --all --exclude plume-front --exclude plume-macro"
+        + " --no-run --no-default-features --features=" + db
+    ]
+);
+
+// PIPELINE 4: runs integration tests
+// It installs a local instance an run integration test with Python scripts
+// that use Selenium (located in scripts/browser_test).
+local Integration(db) = basePipeline(
+    "integration-" + db,
+    [
+        restoreCache,
+        startDb(db),
+        {
+            name: 'selenium',
+            image: 'elgalu/selenium:latest',
+            detach: true,
+        },
+        {
+            name: "integration",
+            image: plumeEnv,
+            environment: {
+                BROWSER: "firefox",
+                DATABASE_URL: if db == "postgres" then "postgres://plume:password@start-db/plume" else "plume.db",
+            },
+            commands: [
+                // Install the front-end
+                "cargo web deploy -p plume-front",
+                // Install the server
+                'cargo install --debug --no-default-features --features="'
+                + db + '",test --force --path .',
+                // Install plm
+                'cargo install --debug --no-default-features --features="'
+                + db + '" --force --path plume-cli',
+                // Run the tests
+                "./script/run_browser_test.sh"
+            ],
+        },
+        saveCache,
+    ]
+);
+
+// PIPELINE 5: make a release build and save artifacts
+//
+// It should also deploy the SQlite build to a test instance
+// located at https://pr-XXX.joinplu.me (but this system is not very
+// stable, and often breaks).
+local Release(db) = basePipeline(
+    "release-" + db,
+    [
+        restoreCache,
+        {
+            name: 'release-' + db,
+            image: plumeEnv,
+            commands: [
+                "cargo web deploy -p plume-front --release",
+                "cargo build --release --no-default-features --features=" + db + " -p plume",
+                "cargo build --release --no-default-features --features=" + db + " -p plume-cli",
+                "./script/generate_artifact.sh",
+            ] + if db == "sqlite" then
+            [ "./script/upload_test_environment.sh" ] else
+            []
+        },
+        upload('artifacts-' + db, '*.tar.gz'),
+        saveCache,
+    ]
+
+);
+
+// PIPELINE 6: upload the new PO templates (.pot) to Crowdin
+//
+// TODO: run only on master
+local PushTranslations() = basePipeline(
+    "push-translations",
+    [
+        {
+            name: "push-translations",
+            image: plumeEnv,
+            commands: [
+                "cargo build",
+                "crowdin upload -b master"
+            ]
+        }
+    ]
+);
+
+// And finally, the list of all our pipelines:
+[
+    CargoFmt(),
+    Clippy("postgres"),
+    Clippy("sqlite"),
+    Unit("postgres"),
+    Unit("sqlite"),
+    Integration("postgres"),
+    Integration("sqlite"),
+    Release("postgres"),
+    Release("sqlite"),
+    PushTranslations()
+]

Cargo.toml

@@ -24,7 +24,6 @@ rocket = "0.4.2"
 rocket_contrib = { version = "0.4.2", features = ["json"] }
 rocket_i18n = { git = "https://github.com/Plume-org/rocket_i18n", rev = "e922afa7c366038b3433278c03b1456b346074f2" }
 rpassword = "4.0"
-runtime-fmt = "0.4.0"
 scheduled-thread-pool = "0.2.2"
 serde = "1.0"
 serde_json = "1.0"
@@ -79,6 +78,7 @@ postgres = ["plume-models/postgres", "diesel/postgres"]
 sqlite = ["plume-models/sqlite", "diesel/sqlite"]
 debug-mailer = []
 test = []
+search-lindera = ["plume-models/search-lindera"]
 
 [workspace]
 members = ["plume-api", "plume-cli", "plume-models", "plume-common", "plume-front", "plume-macro"]

assets/themes/default/_variables.scss

@@ -1,10 +1,10 @@
 /* Color Scheme */
-$gray: #F3F3F3;
+$gray: #f3f3f3;
 $black: #242424;
-$white: #F8F8F8;
-$purple: #7765E3;
+$white: #f8f8f8;
+$purple: #7765e3;
 $lightpurple: #c2bbee;
-$red: #E92F2F;
+$red: #e92f2f;
 $yellow: #ffe347;
 $green: #23f0c7;
 
@@ -24,14 +24,14 @@ $margin: 0 $horizontal-margin;
 
 /* Fonts */
 
-$route159: "Route159", serif;
-$playfair: "Playfair Display", serif;
-$lora: "Lora", serif;
+$route159: "Shabnam", "Route159", serif;
+$playfair: "Vazir", "Playfair Display", serif;
+$lora: "Vazir", "Lora", serif;
 
 //Code Highlighting
 $code-keyword-color: #45244a;
 $code-source-color: #4c588c;
-$code-constant-color: scale-color(magenta,$lightness:-5%);
-$code-operator-color: scale-color($code-source-color,$lightness:-5%);
+$code-constant-color: scale-color(magenta, $lightness: -5%);
+$code-operator-color: scale-color($code-source-color, $lightness: -5%);
 $code-string-color: #8a571c;
 $code-comment-color: #1c4c8a;

assets/themes/default/dark.scss

@@ -1,12 +1,14 @@
 /* color palette: https://coolors.co/23f0c7-ef767a-7765e3-6457a6-ffe347 */
 
-@import url('./feather.css');
-@import url('./fonts/Route159/Route159.css');
-@import url('./fonts/Lora/Lora.css');
-@import url('./fonts/Playfair_Display/PlayfairDisplay.css');
+@import url("./feather.css");
+@import url("./fonts/Route159/Route159.css");
+@import url("./fonts/Lora/Lora.css");
+@import url("./fonts/Playfair_Display/PlayfairDisplay.css");
+@import url("./fonts/Vazir_WOL/Vazir_WOL.css");
+@import url("./fonts/Shabnam_WOL/Shabnam_WOL.css");
 
-@import 'dark_variables';
-@import 'global';
-@import 'header';
-@import 'article';
-@import 'forms';
+@import "dark_variables";
+@import "global";
+@import "header";
+@import "article";
+@import "forms";

assets/themes/default/fonts/Shabnam_WOL/LICENSE

@@ -0,0 +1,94 @@
+Copyright (c) 2015, Saber Rastikerdar (saber.rastikerdar@gmail.com),
+Glyphs and data from Roboto font are licensed under the Apache License, Version 2.0.
+
+This Font Software is licensed under the SIL Open Font License, Version 1.1.
+This license is copied below, and is also available with a FAQ at:
+http://scripts.sil.org/OFL
+
+
+-----------------------------------------------------------
+SIL OPEN FONT LICENSE Version 1.1 - 26 February 2007
+-----------------------------------------------------------
+
+PREAMBLE
+The goals of the Open Font License (OFL) are to stimulate worldwide
+development of collaborative font projects, to support the font creation
+efforts of academic and linguistic communities, and to provide a free and
+open framework in which fonts may be shared and improved in partnership
+with others.
+
+The OFL allows the licensed fonts to be used, studied, modified and
+redistributed freely as long as they are not sold by themselves. The
+fonts, including any derivative works, can be bundled, embedded, 
+redistributed and/or sold with any software provided that any reserved
+names are not used by derivative works. The fonts and derivatives,
+however, cannot be released under any other type of license. The
+requirement for fonts to remain under this license does not apply
+to any document created using the fonts or their derivatives.
+
+DEFINITIONS
+"Font Software" refers to the set of files released by the Copyright
+Holder(s) under this license and clearly marked as such. This may
+include source files, build scripts and documentation.
+
+"Reserved Font Name" refers to any names specified as such after the
+copyright statement(s).
+
+"Original Version" refers to the collection of Font Software components as
+distributed by the Copyright Holder(s).
+
+"Modified Version" refers to any derivative made by adding to, deleting,
+or substituting -- in part or in whole -- any of the components of the
+Original Version, by changing formats or by porting the Font Software to a
+new environment.
+
+"Author" refers to any designer, engineer, programmer, technical
+writer or other person who contributed to the Font Software.
+
+PERMISSION & CONDITIONS
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of the Font Software, to use, study, copy, merge, embed, modify,
+redistribute, and sell modified and unmodified copies of the Font
+Software, subject to the following conditions:
+
+1) Neither the Font Software nor any of its individual components,
+in Original or Modified Versions, may be sold by itself.
+
+2) Original or Modified Versions of the Font Software may be bundled,
+redistributed and/or sold with any software, provided that each copy
+contains the above copyright notice and this license. These can be
+included either as stand-alone text files, human-readable headers or
+in the appropriate machine-readable metadata fields within text or
+binary files as long as those fields can be easily viewed by the user.
+
+3) No Modified Version of the Font Software may use the Reserved Font
+Name(s) unless explicit written permission is granted by the corresponding
+Copyright Holder. This restriction only applies to the primary font name as
+presented to the users.
+
+4) The name(s) of the Copyright Holder(s) or the Author(s) of the Font
+Software shall not be used to promote, endorse or advertise any
+Modified Version, except to acknowledge the contribution(s) of the
+Copyright Holder(s) and the Author(s) or with their explicit written
+permission.
+
+5) The Font Software, modified or unmodified, in part or in whole,
+must be distributed entirely under this license, and must not be
+distributed under any other license. The requirement for fonts to
+remain under this license does not apply to any document created
+using the Font Software.
+
+TERMINATION
+This license becomes null and void if any of the above conditions are
+not met.
+
+DISCLAIMER
+THE FONT SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO ANY WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT
+OF COPYRIGHT, PATENT, TRADEMARK, OR OTHER RIGHT. IN NO EVENT SHALL THE
+COPYRIGHT HOLDER BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+INCLUDING ANY GENERAL, SPECIAL, INDIRECT, INCIDENTAL, OR CONSEQUENTIAL
+DAMAGES, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+FROM, OUT OF THE USE OR INABILITY TO USE THE FONT SOFTWARE OR FROM
+OTHER DEALINGS IN THE FONT SOFTWARE.

assets/themes/default/fonts/Shabnam_WOL/Shabnam_WOL.css

@@ -0,0 +1,49 @@
+@font-face {
+    font-family: Shabnam;
+    src: url("Shabnam-WOL.eot");
+    src: url("Shabnam-WOL.eot?#iefix") format("embedded-opentype"),
+        url("Shabnam-WOL.woff2") format("woff2"),
+        url("Shabnam-WOL.woff") format("woff"),
+        url("Shabnam-WOL.ttf") format("truetype");
+    font-weight: normal;
+}
+
+@font-face {
+    font-family: Shabnam;
+    src: url("Shabnam-Bold-WOL.eot");
+    src: url("Shabnam-Bold-WOL.eot?#iefix") format("embedded-opentype"),
+        url("Shabnam-Bold-WOL.woff2") format("woff2"),
+        url("Shabnam-Bold-WOL.woff") format("woff"),
+        url("Shabnam-Bold-WOL.ttf") format("truetype");
+    font-weight: bold;
+}
+
+@font-face {
+    font-family: Shabnam;
+    src: url("Shabnam-Thin-WOL.eot");
+    src: url("Shabnam-Thin-WOL.eot?#iefix") format("embedded-opentype"),
+        url("Shabnam-Thin-WOL.woff2") format("woff2"),
+        url("Shabnam-Thin-WOL.woff") format("woff"),
+        url("Shabnam-Thin-WOL.ttf") format("truetype");
+    font-weight: 100;
+}
+
+@font-face {
+    font-family: Shabnam;
+    src: url("Shabnam-Light-WOL.eot");
+    src: url("Shabnam-Light-WOL.eot?#iefix") format("embedded-opentype"),
+        url("Shabnam-Light-WOL.woff2") format("woff2"),
+        url("Shabnam-Light-WOL.woff") format("woff"),
+        url("Shabnam-Light-WOL.ttf") format("truetype");
+    font-weight: 300;
+}
+
+@font-face {
+    font-family: Shabnam;
+    src: url("Shabnam-Medium-WOL.eot");
+    src: url("Shabnam-Medium-WOL.eot?#iefix") format("embedded-opentype"),
+        url("Shabnam-Medium-WOL.woff2") format("woff2"),
+        url("Shabnam-Medium-WOL.woff") format("woff"),
+        url("Shabnam-Medium-WOL.ttf") format("truetype");
+    font-weight: 500;
+}

assets/themes/default/fonts/Vazir_WOL/LICENSE

@@ -0,0 +1,51 @@
+Changes by Saber Rastikerdar (saber.rastikerdar@gmail.com) are in public domain.
+Glyphs and data from Roboto font are licensed under the Apache License, Version 2.0.
+
+Fonts are (c) Bitstream (see below). DejaVu changes are in public domain. 
+
+Bitstream Vera Fonts Copyright
+------------------------------
+
+Copyright (c) 2003 by Bitstream, Inc. All Rights Reserved. Bitstream Vera is
+a trademark of Bitstream, Inc.
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of the fonts accompanying this license ("Fonts") and associated
+documentation files (the "Font Software"), to reproduce and distribute the
+Font Software, including without limitation the rights to use, copy, merge,
+publish, distribute, and/or sell copies of the Font Software, and to permit
+persons to whom the Font Software is furnished to do so, subject to the
+following conditions:
+
+The above copyright and trademark notices and this permission notice shall
+be included in all copies of one or more of the Font Software typefaces.
+
+The Font Software may be modified, altered, or added to, and in particular
+the designs of glyphs or characters in the Fonts may be modified and
+additional glyphs or characters may be added to the Fonts, only if the fonts
+are renamed to names not containing either the words "Bitstream" or the word
+"Vera".
+
+This License becomes null and void to the extent applicable to Fonts or Font
+Software that has been modified and is distributed under the "Bitstream
+Vera" names.
+
+The Font Software may be sold as part of a larger software package but no
+copy of one or more of the Font Software typefaces may be sold by itself.
+
+THE FONT SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+OR IMPLIED, INCLUDING BUT NOT LIMITED TO ANY WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF COPYRIGHT, PATENT,
+TRADEMARK, OR OTHER RIGHT. IN NO EVENT SHALL BITSTREAM OR THE GNOME
+FOUNDATION BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, INCLUDING
+ANY GENERAL, SPECIAL, INDIRECT, INCIDENTAL, OR CONSEQUENTIAL DAMAGES,
+WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF
+THE USE OR INABILITY TO USE THE FONT SOFTWARE OR FROM OTHER DEALINGS IN THE
+FONT SOFTWARE.
+
+Except as contained in this notice, the names of Gnome, the Gnome
+Foundation, and Bitstream Inc., shall not be used in advertising or
+otherwise to promote the sale, use or other dealings in this Font Software
+without prior written authorization from the Gnome Foundation or Bitstream
+Inc., respectively. For further information, contact: fonts at gnome dot
+org. 

assets/themes/default/fonts/Vazir_WOL/Vazir_WOL.css

@@ -0,0 +1,65 @@
+@font-face {
+    font-family: Vazir;
+    src: url('Vazir-WOL.eot');
+    src: url('Vazir-WOL.eot?#iefix') format('embedded-opentype'),
+        url('Vazir-WOL.woff2') format('woff2'),
+        url('Vazir-WOL.woff') format('woff'),
+        url('Vazir-WOL.ttf') format('truetype');
+    font-weight: normal;
+    font-style: normal;
+}
+
+@font-face {
+    font-family: Vazir;
+    src: url('Vazir-Bold-WOL.eot');
+    src: url('Vazir-Bold-WOL.eot?#iefix') format('embedded-opentype'),
+        url('Vazir-Bold-WOL.woff2') format('woff2'),
+        url('Vazir-Bold-WOL.woff') format('woff'),
+        url('Vazir-Bold-WOL.ttf') format('truetype');
+    font-weight: bold;
+    font-style: normal;
+}
+
+@font-face {
+    font-family: Vazir;
+    src: url('Vazir-Black-WOL.eot');
+    src: url('Vazir-Black-WOL.eot?#iefix') format('embedded-opentype'),
+        url('Vazir-Black-WOL.woff2') format('woff2'),
+        url('Vazir-Black-WOL.woff') format('woff'),
+        url('Vazir-Black-WOL.ttf') format('truetype');
+    font-weight: 900;
+    font-style: normal;
+}
+
+@font-face {
+    font-family: Vazir;
+    src: url('Vazir-Medium-WOL.eot');
+    src: url('Vazir-Medium-WOL.eot?#iefix') format('embedded-opentype'),
+        url('Vazir-Medium-WOL.woff2') format('woff2'),
+        url('Vazir-Medium-WOL.woff') format('woff'),
+        url('Vazir-Medium-WOL.ttf') format('truetype');
+    font-weight: 500;
+    font-style: normal;
+}
+
+@font-face {
+    font-family: Vazir;
+    src: url('Vazir-Light-WOL.eot');
+    src: url('Vazir-Light-WOL.eot?#iefix') format('embedded-opentype'),
+        url('Vazir-Light-WOL.woff2') format('woff2'),
+        url('Vazir-Light-WOL.woff') format('woff'),
+        url('Vazir-Light-WOL.ttf') format('truetype');
+    font-weight: 300;
+    font-style: normal;
+}
+
+@font-face {
+    font-family: Vazir;
+    src: url('Vazir-Thin-WOL.eot');
+    src: url('Vazir-Thin-WOL.eot?#iefix') format('embedded-opentype'),
+        url('Vazir-Thin-WOL.woff2') format('woff2'),
+        url('Vazir-Thin-WOL.woff') format('woff'),
+        url('Vazir-Thin-WOL.ttf') format('truetype');
+    font-weight: 100;
+    font-style: normal;
+}

assets/themes/default/light.scss

@@ -1,12 +1,14 @@
 /* color palette: https://coolors.co/23f0c7-ef767a-7765e3-6457a6-ffe347 */
 
-@import url('./feather.css');
-@import url('./fonts/Route159/Route159.css');
-@import url('./fonts/Lora/Lora.css');
-@import url('./fonts/Playfair_Display/PlayfairDisplay.css');
+@import url("./feather.css");
+@import url("./fonts/Route159/Route159.css");
+@import url("./fonts/Lora/Lora.css");
+@import url("./fonts/Playfair_Display/PlayfairDisplay.css");
+@import url("./fonts/Vazir_WOL/Vazir_WOL.css");
+@import url("./fonts/Shabnam_WOL/Shabnam_WOL.css");
 
-@import 'variables';
-@import 'global';
-@import 'header';
-@import 'article';
-@import 'forms';
+@import "variables";
+@import "global";
+@import "header";
+@import "article";
+@import "forms";

plume-cli/Cargo.toml

@@ -23,3 +23,4 @@ path = "../plume-models"
 [features]
 postgres = ["plume-models/postgres", "diesel/postgres"]
 sqlite = ["plume-models/sqlite", "diesel/sqlite"]
+search-lindera = ["plume-models/search-lindera"]

plume-cli/src/search.rs

@@ -82,7 +82,7 @@ fn init<'a>(args: &ArgMatches<'a>, conn: &Connection) {
         }
     };
     if can_do || force {
-        let searcher = Searcher::create(&path).unwrap();
+        let searcher = Searcher::create(&path, &CONFIG.search_tokenizers).unwrap();
         refill(args, conn, Some(searcher));
     } else {
         eprintln!(
@@ -98,7 +98,8 @@ fn refill<'a>(args: &ArgMatches<'a>, conn: &Connection, searcher: Option<Searche
         Some(path) => Path::new(path).join("search_index"),
         None => Path::new(&CONFIG.search_index).to_path_buf(),
     };
-    let searcher = searcher.unwrap_or_else(|| Searcher::open(&path).unwrap());
+    let searcher =
+        searcher.unwrap_or_else(|| Searcher::open(&path, &CONFIG.search_tokenizers).unwrap());
 
     searcher.fill(conn).expect("Couldn't import post");
     println!("Commiting result");

plume-common/src/utils.rs

@@ -442,6 +442,7 @@ mod tests {
             ("not_a#hashtag", vec![]),
             ("#نرم‌افزار_آزاد", vec!["نرم‌افزار_آزاد"]),
             ("[#hash in link](https://example.org/)", vec![]),
+            ("#zwsp\u{200b}inhash", vec!["zwsp"]),
         ];
 
         for (md, mentions) in tests {

plume-front/src/main.rs

@@ -19,6 +19,7 @@ init_i18n!(
     en,
     eo,
     es,
+    fa,
     fr,
     gl,
     hi,

plume-models/Cargo.toml

@@ -22,7 +22,7 @@ scheduled-thread-pool = "0.2.2"
 serde = "1.0"
 serde_derive = "1.0"
 serde_json = "1.0"
-tantivy = "0.10.1"
+tantivy = "0.12.0"
 url = "2.1"
 walkdir = "2.2"
 webfinger = "0.4.1"
@@ -30,6 +30,7 @@ whatlang = "0.7.1"
 shrinkwraprs = "0.2.1"
 diesel-derive-newtype = "0.1.2"
 glob = "0.3.0"
+lindera-tantivy = { version = "0.1.2", optional = true }
 
 [dependencies.chrono]
 features = ["serde"]
@@ -54,3 +55,4 @@ diesel_migrations = "1.3.0"
 [features]
 postgres = ["diesel/postgres", "plume-macro/postgres" ]
 sqlite = ["diesel/sqlite", "plume-macro/sqlite" ]
+search-lindera = ["lindera-tantivy"]

plume-models/src/blogs.rs

@@ -498,6 +498,7 @@ pub(crate) mod tests {
     use super::*;
     use crate::{
         blog_authors::*,
+        config::CONFIG,
         instance::tests as instance_tests,
         medias::NewMedia,
         search::tests::get_searcher,
@@ -767,7 +768,9 @@ pub(crate) mod tests {
         conn.test_transaction::<_, (), _>(|| {
             let (_, blogs) = fill_database(conn);
 
-            blogs[0].delete(conn, &get_searcher()).unwrap();
+            blogs[0]
+                .delete(conn, &get_searcher(&CONFIG.search_tokenizers))
+                .unwrap();
             assert!(Blog::get(conn, blogs[0].id).is_err());
             Ok(())
         })
@@ -777,7 +780,7 @@ pub(crate) mod tests {
     fn delete_via_user() {
         let conn = &db();
         conn.test_transaction::<_, (), _>(|| {
-            let searcher = get_searcher();
+            let searcher = get_searcher(&CONFIG.search_tokenizers);
             let (user, _) = fill_database(conn);
 
             let b1 = Blog::insert(

plume-models/src/config.rs

@@ -1,3 +1,4 @@
+use crate::search::TokenizerKind as SearchTokenizer;
 use rocket::config::Limits;
 use rocket::Config as RocketConfig;
 use std::env::{self, var};
@@ -14,6 +15,7 @@ pub struct Config {
     pub db_max_size: Option<u32>,
     pub db_min_idle: Option<u32>,
     pub search_index: String,
+    pub search_tokenizers: SearchTokenizerConfig,
     pub rocket: Result<RocketConfig, RocketError>,
     pub logo: LogoConfig,
     pub default_theme: String,
@@ -188,6 +190,56 @@ impl Default for LogoConfig {
     }
 }
 
+pub struct SearchTokenizerConfig {
+    pub tag_tokenizer: SearchTokenizer,
+    pub content_tokenizer: SearchTokenizer,
+    pub property_tokenizer: SearchTokenizer,
+}
+
+impl SearchTokenizerConfig {
+    pub fn init() -> Self {
+        use SearchTokenizer::*;
+
+        match var("SEARCH_LANG").ok().as_deref() {
+            Some("ja") => {
+                #[cfg(not(feature = "search-lindera"))]
+                panic!("You need build Plume with search-lindera feature, or execute it with SEARCH_TAG_TOKENIZER=ngram and SEARCH_CONTENT_TOKENIZER=ngram to enable Japanese search feature");
+                #[cfg(feature = "search-lindera")]
+                Self {
+                    tag_tokenizer: Self::determine_tokenizer("SEARCH_TAG_TOKENIZER", Lindera),
+                    content_tokenizer: Self::determine_tokenizer(
+                        "SEARCH_CONTENT_TOKENIZER",
+                        Lindera,
+                    ),
+                    property_tokenizer: Ngram,
+                }
+            }
+            _ => Self {
+                tag_tokenizer: Self::determine_tokenizer("SEARCH_TAG_TOKENIZER", Whitespace),
+                content_tokenizer: Self::determine_tokenizer("SEARCH_CONTENT_TOKENIZER", Simple),
+                property_tokenizer: Ngram,
+            },
+        }
+    }
+
+    fn determine_tokenizer(var_name: &str, default: SearchTokenizer) -> SearchTokenizer {
+        use SearchTokenizer::*;
+
+        match var(var_name).ok().as_deref() {
+            Some("simple") => Simple,
+            Some("ngram") => Ngram,
+            Some("whitespace") => Whitespace,
+            Some("lindera") => {
+                #[cfg(not(feature = "search-lindera"))]
+                panic!("You need build Plume with search-lindera feature to use Lindera tokenizer");
+                #[cfg(feature = "search-lindera")]
+                Lindera
+            }
+            _ => default,
+        }
+    }
+}
+
 lazy_static! {
     pub static ref CONFIG: Config = Config {
         base_url: var("BASE_URL").unwrap_or_else(|_| format!(
@@ -209,6 +261,7 @@ lazy_static! {
         #[cfg(feature = "sqlite")]
         database_url: var("DATABASE_URL").unwrap_or_else(|_| format!("{}.sqlite", DB_NAME)),
         search_index: var("SEARCH_INDEX").unwrap_or_else(|_| "search_index".to_owned()),
+        search_tokenizers: SearchTokenizerConfig::init(),
         rocket: get_rocket_config(),
         logo: LogoConfig::default(),
         default_theme: var("DEFAULT_THEME").unwrap_or_else(|_| "default-light".to_owned()),

plume-models/src/lib.rs

@@ -320,7 +320,7 @@ mod tests {
     pub fn rockets() -> super::PlumeRocket {
         super::PlumeRocket {
             conn: db_conn::DbConn((*DB_POOL).get().unwrap()),
-            searcher: Arc::new(search::tests::get_searcher()),
+            searcher: Arc::new(search::tests::get_searcher(&CONFIG.search_tokenizers)),
             worker: Arc::new(ScheduledThreadPool::new(2)),
             user: None,
         }

plume-models/src/search/mod.rs

@@ -3,10 +3,11 @@ mod searcher;
 mod tokenizer;
 pub use self::query::PlumeQuery as Query;
 pub use self::searcher::*;
+pub use self::tokenizer::TokenizerKind;
 
 #[cfg(test)]
 pub(crate) mod tests {
-    use super::{Query, Searcher};
+    use super::{Query, Searcher, TokenizerKind};
     use diesel::Connection;
     use plume_common::utils::random_hex;
     use std::env::temp_dir;
@@ -14,18 +15,20 @@ pub(crate) mod tests {
 
     use crate::{
         blogs::tests::fill_database,
+        config::SearchTokenizerConfig,
         post_authors::*,
         posts::{NewPost, Post},
         safe_string::SafeString,
         tests::db,
+        CONFIG,
     };
 
-    pub(crate) fn get_searcher() -> Searcher {
+    pub(crate) fn get_searcher(tokenizers: &SearchTokenizerConfig) -> Searcher {
         let dir = temp_dir().join(&format!("plume-test-{}", random_hex()));
         if dir.exists() {
-            Searcher::open(&dir)
+            Searcher::open(&dir, tokenizers)
         } else {
-            Searcher::create(&dir)
+            Searcher::create(&dir, tokenizers)
         }
         .unwrap()
     }
@@ -100,27 +103,27 @@ pub(crate) mod tests {
     fn open() {
         let dir = temp_dir().join(format!("plume-test-{}", random_hex()));
         {
-            Searcher::create(&dir).unwrap();
+            Searcher::create(&dir, &CONFIG.search_tokenizers).unwrap();
         }
-        Searcher::open(&dir).unwrap();
+        Searcher::open(&dir, &CONFIG.search_tokenizers).unwrap();
     }
 
     #[test]
     fn create() {
         let dir = temp_dir().join(format!("plume-test-{}", random_hex()));
 
-        assert!(Searcher::open(&dir).is_err());
+        assert!(Searcher::open(&dir, &CONFIG.search_tokenizers).is_err());
         {
-            Searcher::create(&dir).unwrap();
+            Searcher::create(&dir, &CONFIG.search_tokenizers).unwrap();
         }
-        Searcher::open(&dir).unwrap(); //verify it's well created
+        Searcher::open(&dir, &CONFIG.search_tokenizers).unwrap(); //verify it's well created
     }
 
     #[test]
     fn search() {
         let conn = &db();
         conn.test_transaction::<_, (), _>(|| {
-            let searcher = get_searcher();
+            let searcher = get_searcher(&CONFIG.search_tokenizers);
             let blog = &fill_database(conn).1[0];
             let author = &blog.list_authors(conn).unwrap()[0];
 
@@ -180,10 +183,69 @@ pub(crate) mod tests {
         });
     }
 
+    #[cfg(feature = "search-lindera")]
+    #[test]
+    fn search_japanese() {
+        let conn = &db();
+        conn.test_transaction::<_, (), _>(|| {
+            let tokenizers = SearchTokenizerConfig {
+                tag_tokenizer: TokenizerKind::Lindera,
+                content_tokenizer: TokenizerKind::Lindera,
+                property_tokenizer: TokenizerKind::Ngram,
+            };
+            let searcher = get_searcher(&tokenizers);
+            let blog = &fill_database(conn).1[0];
+
+            let title = random_hex()[..8].to_owned();
+
+            let post = Post::insert(
+                conn,
+                NewPost {
+                    blog_id: blog.id,
+                    slug: title.clone(),
+                    title: title.clone(),
+                    content: SafeString::new("ブログエンジンPlumeです。"),
+                    published: true,
+                    license: "CC-BY-SA".to_owned(),
+                    ap_url: "".to_owned(),
+                    creation_date: None,
+                    subtitle: "".to_owned(),
+                    source: "".to_owned(),
+                    cover_id: None,
+                },
+                &searcher,
+            )
+            .unwrap();
+
+            searcher.commit();
+
+            assert_eq!(
+                searcher.search_document(conn, Query::from_str("ブログエンジン").unwrap(), (0, 1))
+                    [0]
+                .id,
+                post.id
+            );
+            assert_eq!(
+                searcher.search_document(conn, Query::from_str("Plume").unwrap(), (0, 1))[0].id,
+                post.id
+            );
+            assert_eq!(
+                searcher.search_document(conn, Query::from_str("です").unwrap(), (0, 1))[0].id,
+                post.id
+            );
+            assert_eq!(
+                searcher.search_document(conn, Query::from_str("。").unwrap(), (0, 1))[0].id,
+                post.id
+            );
+
+            Ok(())
+        });
+    }
+
     #[test]
     fn drop_writer() {
-        let searcher = get_searcher();
+        let searcher = get_searcher(&CONFIG.search_tokenizers);
         searcher.drop_writer();
-        get_searcher();
+        get_searcher(&CONFIG.search_tokenizers);
     }
 }

plume-models/src/search/searcher.rs

@@ -1,18 +1,14 @@
 use crate::{
-    instance::Instance,
-    posts::Post,
-    schema::posts,
-    search::{query::PlumeQuery, tokenizer},
-    tags::Tag,
-    Connection, Result,
+    config::SearchTokenizerConfig, instance::Instance, posts::Post, schema::posts,
+    search::query::PlumeQuery, tags::Tag, Connection, Result,
 };
 use chrono::Datelike;
 use diesel::{ExpressionMethods, QueryDsl, RunQueryDsl};
 use itertools::Itertools;
 use std::{cmp, fs::create_dir_all, path::Path, sync::Mutex};
 use tantivy::{
-    collector::TopDocs, directory::MmapDirectory, schema::*, tokenizer::*, Index, IndexReader,
-    IndexWriter, ReloadPolicy, Term,
+    collector::TopDocs, directory::MmapDirectory, schema::*, Index, IndexReader, IndexWriter,
+    ReloadPolicy, Term,
 };
 use whatlang::{detect as detect_lang, Lang};
 
@@ -34,7 +30,7 @@ impl Searcher {
     pub fn schema() -> Schema {
         let tag_indexing = TextOptions::default().set_indexing_options(
             TextFieldIndexing::default()
-                .set_tokenizer("whitespace_tokenizer")
+                .set_tokenizer("tag_tokenizer")
                 .set_index_option(IndexRecordOption::Basic),
         );
 
@@ -70,15 +66,7 @@ impl Searcher {
         schema_builder.build()
     }
 
-    pub fn create(path: &dyn AsRef<Path>) -> Result<Self> {
-        let whitespace_tokenizer = tokenizer::WhitespaceTokenizer.filter(LowerCaser);
-
-        let content_tokenizer = SimpleTokenizer
-            .filter(RemoveLongFilter::limit(40))
-            .filter(LowerCaser);
-
-        let property_tokenizer = NgramTokenizer::new(2, 8, false).filter(LowerCaser);
-
+    pub fn create(path: &dyn AsRef<Path>, tokenizers: &SearchTokenizerConfig) -> Result<Self> {
         let schema = Self::schema();
 
         create_dir_all(path).map_err(|_| SearcherError::IndexCreationError)?;
@@ -90,9 +78,9 @@ impl Searcher {
 
         {
             let tokenizer_manager = index.tokenizers();
-            tokenizer_manager.register("whitespace_tokenizer", whitespace_tokenizer);
-            tokenizer_manager.register("content_tokenizer", content_tokenizer);
-            tokenizer_manager.register("property_tokenizer", property_tokenizer);
+            tokenizer_manager.register("tag_tokenizer", tokenizers.tag_tokenizer);
+            tokenizer_manager.register("content_tokenizer", tokenizers.content_tokenizer);
+            tokenizer_manager.register("property_tokenizer", tokenizers.property_tokenizer);
         } //to please the borrow checker
         Ok(Self {
             writer: Mutex::new(Some(
@@ -109,31 +97,38 @@ impl Searcher {
         })
     }
 
-    pub fn open(path: &dyn AsRef<Path>) -> Result<Self> {
-        let whitespace_tokenizer = tokenizer::WhitespaceTokenizer.filter(LowerCaser);
-
-        let content_tokenizer = SimpleTokenizer
-            .filter(RemoveLongFilter::limit(40))
-            .filter(LowerCaser);
-
-        let property_tokenizer = NgramTokenizer::new(2, 8, false).filter(LowerCaser);
-
-        let index =
+    pub fn open(path: &dyn AsRef<Path>, tokenizers: &SearchTokenizerConfig) -> Result<Self> {
+        let mut index =
             Index::open(MmapDirectory::open(path).map_err(|_| SearcherError::IndexOpeningError)?)
                 .map_err(|_| SearcherError::IndexOpeningError)?;
 
         {
             let tokenizer_manager = index.tokenizers();
-            tokenizer_manager.register("whitespace_tokenizer", whitespace_tokenizer);
-            tokenizer_manager.register("content_tokenizer", content_tokenizer);
-            tokenizer_manager.register("property_tokenizer", property_tokenizer);
+            tokenizer_manager.register("tag_tokenizer", tokenizers.tag_tokenizer);
+            tokenizer_manager.register("content_tokenizer", tokenizers.content_tokenizer);
+            tokenizer_manager.register("property_tokenizer", tokenizers.property_tokenizer);
         } //to please the borrow checker
-        let mut writer = index
+        let writer = index
             .writer(50_000_000)
             .map_err(|_| SearcherError::WriteLockAcquisitionError)?;
-        writer
-            .garbage_collect_files()
+
+        // Since Tantivy v0.12.0, IndexWriter::garbage_collect_files() returns Future.
+        // To avoid conflict with Plume async project, we don't introduce async now.
+        // After async is introduced to Plume, we can use garbage_collect_files() again.
+        // Algorithm stolen from Tantivy's SegmentUpdater::list_files()
+        use std::collections::HashSet;
+        use std::path::PathBuf;
+        let mut files: HashSet<PathBuf> = index
+            .list_all_segment_metas()
+            .into_iter()
+            .flat_map(|segment_meta| segment_meta.list_files())
+            .collect();
+        files.insert(Path::new("meta.json").to_path_buf());
+        index
+            .directory_mut()
+            .garbage_collect(|| files)
             .map_err(|_| SearcherError::IndexEditionError)?;
+
         Ok(Self {
             writer: Mutex::new(Some(writer)),
             reader: index

plume-models/src/search/tokenizer.rs

@@ -1,5 +1,34 @@
+#[cfg(feature = "search-lindera")]
+use lindera_tantivy::tokenizer::LinderaTokenizer;
 use std::str::CharIndices;
-use tantivy::tokenizer::{Token, TokenStream, Tokenizer};
+use tantivy::tokenizer::*;
+
+#[derive(Clone, Copy)]
+pub enum TokenizerKind {
+    Simple,
+    Ngram,
+    Whitespace,
+    #[cfg(feature = "search-lindera")]
+    Lindera,
+}
+
+impl From<TokenizerKind> for TextAnalyzer {
+    fn from(tokenizer: TokenizerKind) -> TextAnalyzer {
+        use TokenizerKind::*;
+
+        match tokenizer {
+            Simple => TextAnalyzer::from(SimpleTokenizer)
+                .filter(RemoveLongFilter::limit(40))
+                .filter(LowerCaser),
+            Ngram => TextAnalyzer::from(NgramTokenizer::new(2, 8, false)).filter(LowerCaser),
+            Whitespace => TextAnalyzer::from(WhitespaceTokenizer).filter(LowerCaser),
+            #[cfg(feature = "search-lindera")]
+            Lindera => {
+                TextAnalyzer::from(LinderaTokenizer::new("decompose", "")).filter(LowerCaser)
+            }
+        }
+    }
+}
 
 /// Tokenize the text by splitting on whitespaces. Pretty much a copy of Tantivy's SimpleTokenizer,
 /// but not splitting on punctuation
@@ -12,15 +41,13 @@ pub struct WhitespaceTokenStream<'a> {
     token: Token,
 }
 
-impl<'a> Tokenizer<'a> for WhitespaceTokenizer {
-    type TokenStreamImpl = WhitespaceTokenStream<'a>;
-
-    fn token_stream(&self, text: &'a str) -> Self::TokenStreamImpl {
-        WhitespaceTokenStream {
+impl Tokenizer for WhitespaceTokenizer {
+    fn token_stream<'a>(&self, text: &'a str) -> BoxTokenStream<'a> {
+        BoxTokenStream::from(WhitespaceTokenStream {
             text,
             chars: text.char_indices(),
             token: Token::default(),
-        }
+        })
     }
 }
 impl<'a> WhitespaceTokenStream<'a> {

plume-models/src/timeline/query.rs

@@ -406,8 +406,8 @@ impl Bool {
                 }
             }
             Bool::HasCover => Ok(post.cover_id.is_some()),
-            Bool::Local => Ok(post.get_blog(&rocket.conn)?.is_local()),
-            Bool::All => Ok(true),
+            Bool::Local => Ok(post.get_blog(&rocket.conn)?.is_local() && kind == Kind::Original),
+            Bool::All => Ok(kind == Kind::Original),
         }
     }
 }

plume-models/src/users.rs

@@ -1026,6 +1026,7 @@ impl NewUser {
 pub(crate) mod tests {
     use super::*;
     use crate::{
+        config::CONFIG,
         instance::{tests as instance_tests, Instance},
         search::tests::get_searcher,
         tests::{db, rockets},
@@ -1122,7 +1123,9 @@ pub(crate) mod tests {
             let inserted = fill_database(conn);
 
             assert!(User::get(conn, inserted[0].id).is_ok());
-            inserted[0].delete(conn, &get_searcher()).unwrap();
+            inserted[0]
+                .delete(conn, &get_searcher(&CONFIG.search_tokenizers))
+                .unwrap();
             assert!(User::get(conn, inserted[0].id).is_err());
             Ok(())
         });

script/browser_test/utils.py

@@ -13,10 +13,12 @@ class Browser(unittest.TestCase):
             raise Exception("No browser was requested")
         capabilities['acceptSslCerts'] = True
         self.driver = webdriver.Remote(
-            command_executor='http://localhost:24444/wd/hub',
+            # The "selenium" address is set up by Drone CI and "points" to the container running selenium
+            command_executor='http://selenium:24444/wd/hub',
             desired_capabilities=capabilities)
     def tearDown(self):
         self.driver.close()
 
     def get(self, url):
+        # Like "selenium", integration is mapped to the container that runs the plume instance
         return self.driver.get("https://localhost" + url)

script/run_browser_test.sh

@@ -12,7 +12,7 @@ plm users new -n admin -N 'Admin' -e 'email@exemple.com' -p 'password'
 plume &
 caddy -conf /Caddyfile &
 
-until curl http://localhost:7878/test/health -f; do sleep 1; done 2>/dev/null >/dev/null
+until curl http://localhost:7878/test/health -f; do sleep 1; done #2>/dev/null >/dev/null
 
 cd $(dirname $0)/browser_test/
 python3 -m unittest *.py

src/main.rs

@@ -6,8 +6,6 @@ extern crate gettext_macros;
 #[macro_use]
 extern crate rocket;
 #[macro_use]
-extern crate runtime_fmt;
-#[macro_use]
 extern crate serde_json;
 #[macro_use]
 extern crate validator_derive;
@@ -28,7 +26,8 @@ use std::sync::{Arc, Mutex};
 use std::time::Duration;
 
 init_i18n!(
-    "plume", ar, bg, ca, cs, de, en, eo, es, fr, gl, hi, hr, it, ja, nb, pl, pt, ro, ru, sr, sk, sv
+    "plume", ar, bg, ca, cs, de, en, eo, es, fa, fr, gl, hi, hr, it, ja, nb, pl, pt, ro, ru, sr,
+    sk, sv
 );
 
 mod api;
@@ -100,7 +99,7 @@ Then try to restart Plume.
     let workpool = ScheduledThreadPool::with_name("worker {}", num_cpus::get());
     // we want a fast exit here, so
     #[allow(clippy::match_wild_err_arm)]
-    let searcher = match UnmanagedSearcher::open(&CONFIG.search_index) {
+    let searcher = match UnmanagedSearcher::open(&CONFIG.search_index, &CONFIG.search_tokenizers) {
         Err(Error::Search(e)) => match e {
             SearcherError::WriteLockAcquisitionError => panic!(
                 r#"

src/routes/posts.rs

@@ -643,7 +643,7 @@ pub fn remote_interact_post(
         .and_then(|blog| Post::find_by_slug(&rockets.conn, &slug, blog.id))?;
     if let Some(uri) = User::fetch_remote_interact_uri(&remote.remote)
         .ok()
-        .and_then(|uri| rt_format!(uri, uri = target.ap_url).ok())
+        .map(|uri| uri.replace("{uri}", &target.ap_url))
     {
         Ok(Redirect::to(uri).into())
     } else {

src/routes/user.rs

@@ -201,15 +201,14 @@ pub fn follow_not_connected(
         if let Some(uri) = User::fetch_remote_interact_uri(&remote_form)
             .ok()
             .and_then(|uri| {
-                rt_format!(
-                    uri,
-                    uri = format!(
+                Some(uri.replace(
+                    "{uri}",
+                    &format!(
                         "{}@{}",
                         target.fqn,
                         target.get_instance(&rockets.conn).ok()?.public_domain
-                    )
-                )
-                .ok()
+                    ),
+                ))
             })
         {
             Ok(Redirect::to(uri).into())