SQLite 3.41.0 and pearson correlation extension function (#106)

* Build SQLite 3.41.0

* Update pivot_vtab

* Add Pearson correlation coefficient function extension, build

* Add an easy way to running test locally without Nodejs

* Use RSS sum to pick top2 processes for the report

* Try previous Ubuntu LTS as a workaround for Firefox worker not starting

.github/workflows/test.yml

@@ -11,7 +11,7 @@ on:
 jobs:
   test:
     name: Run tests
-    runs-on: ubuntu-latest    
+    runs-on: ubuntu-20.04
     steps:
     - uses: actions/checkout@v2
     - name: Use Node.js

Dockerfile.test

@@ -0,0 +1,24 @@
+# An easy way to run tests locally without Nodejs installed:
+#
+#     docker build -t sqliteviz/test -f Dockerfile.test .
+#
+
+FROM node:12
+
+RUN set -ex; \
+    apt update; \
+    apt install -y chromium firefox-esr; \
+    npm install -g npm@7
+
+WORKDIR /tmp/build
+
+COPY package.json package-lock.json ./
+COPY lib lib
+RUN npm install
+
+COPY . .
+
+RUN set -ex; \
+    sed -i 's/browsers: \[.*\],/browsers: ['"'FirefoxHeadlessTouch'"'],/' karma.conf.js
+
+RUN npm run lint -- --no-fix && npm run test

lib/sql-js/Dockerfile

@@ -1,4 +1,4 @@
-FROM emscripten/emsdk:2.0.24
+FROM emscripten/emsdk:3.0.1
 
 WORKDIR /tmp/build
 

lib/sql-js/README.md

@@ -43,6 +43,8 @@ SQLite [miscellaneous extensions][3] included:
 SQLite 3rd party extensions included:
 
 1. [pivot_vtab][5] -- a pivot virtual table
+2. `pearson` correlation coefficient function extension from [sqlean][21]
+   (which is part of [squib][20])
 
 To ease the step to have working clone locally, the build is committed into
 the repository.
@@ -99,3 +101,5 @@ described in [this message from SQLite Forum][12]:
 [17]: https://sqlite.org/contrib/
 [18]: https://sqlite.org/contrib//download/extension-functions.c?get=25
 [19]: https://github.com/lana-k/sqliteviz/blob/master/tests/lib/database/sqliteExtensions.spec.js
+[20]: https://github.com/mrwilson/squib/blob/master/pearson.c
+[21]: https://github.com/nalgeon/sqlean/blob/incubator/src/pearson.c

lib/sql-js/benchmark/README.md

@@ -1,14 +1,25 @@
 # SQLite WebAssembly build micro-benchmark
 
-This directory contains a micro-benchmark for evaluating SQLite
-WebAssembly builds performance on typical SQL queries, run from
-`make.sh` script. It can also serve as a smoke test.
+This directory contains a micro-benchmark for evaluating SQLite WebAssembly
+builds performance on read and write SQL queries, run from `make.sh` script. If
+the script has permission to `nice` processes and [Procpath][1] is installed,
+e.g. it is run with `sudo -E env PATH=$PATH ./make.sh`, it'll `renice` all
+processes running inside the benchmark containers. It can also serve as a smoke
+test (e.g. for memory leaks).
 
-The benchmark operates on a set of SQLite WebAssembly builds expected
-in `lib/build-$NAME` directories each containing `sql-wasm.js` and
-`sql-wasm.wasm`. Then it creates a Docker image for each, and runs
-the benchmark in Firefox and Chromium using Karma in the container.
+The benchmark operates on a set of SQLite WebAssembly builds expected in
+`lib/build-$NAME` directories each containing `sql-wasm.js` and
+`sql-wasm.wasm`. Then it creates a Docker image for each, and runs the
+benchmark in Firefox and Chromium using Karma in the container.
 
-After successful run, the benchmark result of each build is contained
-in `build-$NAME-result.json`. The JSON result files can be analysed
-using `result-analysis.ipynb` Jupyter notebook.
+After successful run, the benchmark produces the following per each build:
+
+- `build-$NAME-result.json`
+- `build-$NAME.sqlite` (if Procpath is installed)
+- `build-$NAME.svg` (if Procpath is installed)
+
+These files can be analysed using `result-analysis.ipynb` Jupyter notebook.
+The SVG is a chart with CPU and RSS usage of each test container (i.e. Chromium
+run, then Firefox run per container).
+
+[1]: https://pypi.org/project/Procpath/

lib/sql-js/benchmark/make.sh

@@ -1,7 +1,8 @@
 #!/bin/bash -e
 
 cleanup () {
-  rm -rf lib/dist $flag_file
+  rm -rf lib/dist "$renice_flag_file"
+  docker rm -f sqljs-benchmark-run 2> /dev/null || true
 }
 trap cleanup EXIT
 
@@ -11,34 +12,36 @@ if [ ! -f sample.csv ]; then
     | gunzip -c > sample.csv
 fi
 
+PLAYBOOK=procpath/karma_docker.procpath
+
 # for renice to work run like "sudo -E env PATH=$PATH ./make.sh"
-test_ni=$(nice -n -1 nice)
-if [ $test_ni == -1 ]; then
-  flag_file=$(mktemp)
+test_ni=$(nice -n -5 nice)
+if [ $test_ni == -5 ]; then
+  renice_flag_file=$(mktemp)
 fi
-(
-  while [ -f $flag_file ]; do
-    root_pid=$(
-      docker ps -f status=running -f name='^sqljs-benchmark-' -q \
-        | xargs -r -I{} -- docker inspect -f '{{.State.Pid}}' {}
-    )
-    if [ ! -z $root_pid ]; then
-      procpath query -d $'\n' "$..children[?(@.stat.pid == $root_pid)]..pid" \
-        | xargs -I{} -- renice -n -1 -p {} > /dev/null
-    fi
-    sleep 1
-  done &
-)
+{
+  while [ -f $renice_flag_file ]; do
+    procpath --logging-level ERROR play -f $PLAYBOOK renice:watch
+  done
+} &
 
 shopt -s nullglob
 for d in lib/build-* ; do
   rm -rf lib/dist
   cp -r $d lib/dist
+  sample_name=$(basename $d)
 
-  name=$(basename $d)
-  docker build -t sqliteviz/sqljs-benchmark:$name .
-  docker rm sqljs-benchmark-$name 2> /dev/null || true
-  docker run -it --cpus 2 --name sqljs-benchmark-$name sqliteviz/sqljs-benchmark:$name
-  docker cp sqljs-benchmark-$name:/tmp/build/suite-result.json ${name}-result.json
-  docker rm sqljs-benchmark-$name
+  docker build -t sqliteviz/sqljs-benchmark .
+  docker rm sqljs-benchmark-run 2> /dev/null || true
+  docker run -d -it --cpus 2 --name sqljs-benchmark-run sqliteviz/sqljs-benchmark
+  {
+    rm -f ${sample_name}.sqlite
+    procpath play -f $PLAYBOOK -o database_file=${sample_name}.sqlite track:record
+    procpath play -f $PLAYBOOK -o database_file=${sample_name}.sqlite \
+      -o plot_file=${sample_name}.svg track:plot
+  } &
+
+  docker attach sqljs-benchmark-run
+  docker cp sqljs-benchmark-run:/tmp/build/suite-result.json ${sample_name}-result.json
+  docker rm sqljs-benchmark-run
 done

lib/sql-js/benchmark/procpath/karma_docker.procpath

@@ -0,0 +1,28 @@
+# This command may run when "sqljs-benchmark-run" does not yet exist or run
+[renice:watch]
+interval: 2
+repeat: 30
+environment:
+  ROOT_PID=docker inspect -f "{{.State.Pid}}" sqljs-benchmark-run 2> /dev/null || true
+query:
+  PIDS=$..children[?(@.stat.pid in [$ROOT_PID])]..pid
+command:
+  echo $PIDS | tr , '\n' | xargs --no-run-if-empty -I{} -- renice -n -5 -p {}
+
+# Expected input arguments: database_file
+[track:record]
+interval: 1
+stop_without_result: 1
+environment:
+  ROOT_PID=docker inspect -f "{{.State.Pid}}" sqljs-benchmark-run
+query:
+  $..children[?(@.stat.pid == $ROOT_PID)]
+pid_list: $ROOT_PID
+
+# Expected input arguments: database_file, plot_file
+[track:plot]
+moving_average_window: 5
+title: Chromium vs Firefox (№1 RSS, №2 CPU)
+custom_query_file:
+  procpath/top2_rss.sql
+  procpath/top2_cpu.sql

lib/sql-js/benchmark/procpath/top2_cpu.sql

@@ -0,0 +1,29 @@
+WITH diff_all AS (
+    SELECT
+        record_id,
+        ts,
+        stat_pid,
+        stat_utime + stat_stime - LAG(stat_utime + stat_stime) OVER (
+            PARTITION BY stat_pid
+            ORDER BY record_id
+        ) tick_diff,
+        ts - LAG(ts) OVER (
+            PARTITION BY stat_pid
+            ORDER BY record_id
+        ) ts_diff
+    FROM record
+), diff AS (
+    SELECT * FROM diff_all WHERE tick_diff IS NOT NULL
+), one_time_pid_condition AS (
+    SELECT stat_pid
+    FROM record
+    GROUP BY 1
+    ORDER BY SUM(stat_utime + stat_stime) DESC
+    LIMIT 2
+)
+SELECT
+    ts,
+    stat_pid pid,
+    100.0 * tick_diff / (SELECT value FROM meta WHERE key = 'clock_ticks') / ts_diff value
+FROM diff
+JOIN one_time_pid_condition USING(stat_pid)

lib/sql-js/benchmark/procpath/top2_rss.sql

@@ -0,0 +1,13 @@
+WITH one_time_pid_condition AS (
+    SELECT stat_pid
+    FROM record
+    GROUP BY 1
+    ORDER BY SUM(stat_rss) DESC
+    LIMIT 2
+)
+SELECT
+    ts,
+    stat_pid pid,
+    stat_rss / 1024.0 / 1024 * (SELECT value FROM meta WHERE key = 'page_size') value
+FROM record
+JOIN one_time_pid_condition USING(stat_pid)

lib/sql-js/build.py

@@ -2,9 +2,11 @@ import logging
 import subprocess
 from pathlib import Path
 
-
+# See the setting descriptions on these pages:
+# - https://emscripten.org/docs/optimizing/Optimizing-Code.html
+# - https://github.com/emscripten-core/emscripten/blob/main/src/settings.js
 cflags = (
-    '-O2',
+    # SQLite configuration
     '-DSQLITE_DEFAULT_CACHE_SIZE=-65536',  # 64 MiB
     '-DSQLITE_DEFAULT_MEMSTATUS=0',
     '-DSQLITE_DEFAULT_SYNCHRONOUS=0',
@@ -13,26 +15,26 @@ cflags = (
     '-DSQLITE_ENABLE_FTS3',
     '-DSQLITE_ENABLE_FTS3_PARENTHESIS',
     '-DSQLITE_ENABLE_FTS5',
-    '-DSQLITE_ENABLE_JSON1',
     '-DSQLITE_ENABLE_NORMALIZE',
     '-DSQLITE_EXTRA_INIT=extra_init',
     '-DSQLITE_OMIT_DEPRECATED',
     '-DSQLITE_OMIT_LOAD_EXTENSION',
     '-DSQLITE_OMIT_SHARED_CACHE',
     '-DSQLITE_THREADSAFE=0',
+    # Compile-time optimisation
+    '-Os',  # reduces the code size about in half comparing to -O2
+    '-flto',
 )
 emflags = (
     # Base
     '--memory-init-file', '0',
-    '-s', 'RESERVED_FUNCTION_POINTERS=64',
     '-s', 'ALLOW_TABLE_GROWTH=1',
-    '-s', 'SINGLE_FILE=0',
     # WASM
     '-s', 'WASM=1',
     '-s', 'ALLOW_MEMORY_GROWTH=1',
-    # Optimisation
-    '-s', 'INLINING_LIMIT=50',
-    '-O3',
+    '-s', 'ENVIRONMENT=web,worker',
+    # Link-time optimisation
+    '-Os',
     '-flto',
     # sql.js
     '-s', 'EXPORTED_FUNCTIONS=@src/sqljs/exported_functions.json',
@@ -50,22 +52,22 @@ def build(src: Path, dst: Path):
         'emcc',
         *cflags,
         '-c', src / 'sqlite3.c',
-        '-o', out / 'sqlite3.bc',
+        '-o', out / 'sqlite3.o',
     ])
     logging.info('Building LLVM bitcode for extension-functions.c')
     subprocess.check_call([
         'emcc',
         *cflags,
         '-c', src / 'extension-functions.c',
-        '-o', out / 'extension-functions.bc',
+        '-o', out / 'extension-functions.o',
     ])
 
     logging.info('Building WASM from bitcode')
     subprocess.check_call([
         'emcc',
         *emflags,
-        out / 'sqlite3.bc',
-        out / 'extension-functions.bc',
+        out / 'sqlite3.o',
+        out / 'extension-functions.o',
         '-o', out / 'sql-wasm.js',
     ])
 

lib/sql-js/configure.py

@@ -8,7 +8,7 @@ from pathlib import Path
 from urllib import request
 
 
-amalgamation_url = 'https://sqlite.org/2022/sqlite-amalgamation-3390000.zip'
+amalgamation_url = 'https://sqlite.org/2023/sqlite-amalgamation-3410000.zip'
 
 # Extension-functions
 # ===================
@@ -28,10 +28,11 @@ extension_urls = (
     ('https://sqlite.org/src/raw/09f967dc?at=decimal.c', 'sqlite3_decimal_init'),
     # Third-party extension
     # =====================
-    ('https://github.com/jakethaw/pivot_vtab/raw/08ab0797/pivot_vtab.c', 'sqlite3_pivotvtab_init'),
+    ('https://github.com/jakethaw/pivot_vtab/raw/9323ef93/pivot_vtab.c', 'sqlite3_pivotvtab_init'),
+    ('https://github.com/nalgeon/sqlean/raw/95e8d21a/src/pearson.c', 'sqlite3_pearson_init'),
 )
 
-sqljs_url = 'https://github.com/sql-js/sql.js/archive/refs/tags/v1.5.0.zip'
+sqljs_url = 'https://github.com/sql-js/sql.js/archive/refs/tags/v1.7.0.zip'
 
 
 def _generate_extra_init_c_function(init_function_names):

package.json

@@ -1,6 +1,6 @@
 {
   "name": "sqliteviz",
-  "version": "0.21.0",
+  "version": "0.21.1",
   "license": "Apache-2.0",
   "private": true,
   "scripts": {

src/views/Main/Workspace/Tabs/Tab/SqlEditor/hint.js

@@ -3,14 +3,20 @@ import 'codemirror/addon/hint/show-hint.js'
 import 'codemirror/addon/hint/sql-hint.js'
 import store from '@/store'
 
+function _getHintText (hint) {
+  return typeof hint === 'string' ? hint : hint.text
+}
 export function getHints (cm, options) {
-  const token = cm.getTokenAt(cm.getCursor()).string.toUpperCase()
   const result = CM.hint.sql(cm, options)
+
   // Don't show the hint if there is only one option
-  // and the token is already completed with this option
-  if (result.list.length === 1 && result.list[0].text.toUpperCase() === token) {
+  // and the replacingText is already equals to this option
+  const replacedText = cm.getRange(result.from, result.to).toUpperCase()
+  if (result.list.length === 1 &&
+    _getHintText(result.list[0]).toUpperCase() === replacedText) {
     result.list = []
   }
+
   return result
 }
 

tests/lib/database/sqliteExtensions.spec.js

@@ -293,7 +293,7 @@ describe('SQLite extensions', function () {
 
   it('supports decimal', async function () {
     const actual = await db.execute(`
-      select
+      SELECT
         decimal_add(decimal('0.1'), decimal('0.2')) "add",
         decimal_sub(0.2, 0.1) sub,
         decimal_mul(power(2, 69), 2) mul,
@@ -430,4 +430,29 @@ describe('SQLite extensions', function () {
       ]
     })
   })
+
+  it('supports pearson', async function () {
+    const actual = await db.execute(`
+      CREATE TABLE dataset(x REAL, y REAL, z REAL);
+      INSERT INTO dataset VALUES
+        (5,3,3.2),  (5,6,4.3),  (5,9,5.4),
+        (10,3,4),   (10,6,3.8), (10,9,3.6),
+        (15,3,4.8), (15,6,4),   (15,9,3.5);
+
+      SELECT
+        pearson(x, x) xx,
+        pearson(x, y) xy,
+        abs(-0.12666 - pearson(x, z)) < 0.00001 xz,
+        pearson(y, x) yx,
+        pearson(y, y) yy,
+        abs(0.10555 - pearson(y, z))  < 0.00001 yz,
+        abs(-0.12666 - pearson(z, x)) < 0.00001 zx,
+        abs(0.10555 - pearson(z, y))  < 0.00001 zy,
+        pearson(z, z) zz
+      FROM dataset;
+    `)
+    expect(actual.values).to.eql({
+      xx: [1], xy: [0], xz: [1], yx: [0], yy: [1], yz: [1], zx: [1], zy: [1], zz: [1]
+    })
+  })
 })

tests/views/Main/Workspace/Tabs/Tab/SqlEditor/hint.spec.js

@@ -138,15 +138,37 @@ describe('hint.js', () => {
     'getHints returns [ ] if there is only one option and token is completed with this option',
     () => {
       // mock CM.hint.sql and editor
-      sinon.stub(CM.hint, 'sql').returns({ list: [{ text: 'SELECT' }] })
+      sinon.stub(CM.hint, 'sql').returns({
+        list: [{ text: 'SELECT' }],
+        from: null, // from/to doesn't metter because getRange is mocked
+        to: null
+      })
+
       const editor = {
-        getTokenAt () {
-          return {
-            string: 'select',
-            type: 'keyword'
+        getRange () {
+          return 'select'
+        }
+      }
+
+      const hints = getHints(editor, {})
+      expect(hints.list).to.eql([])
+    }
+  )
+
+  it(
+    'getHints returns [ ] if there is only one string option and token ' +
+    'is completed with this option',
+    () => {
+      // mock CM.hint.sql and editor
+      sinon.stub(CM.hint, 'sql').returns({
+        list: ['house.name'],
+        from: null, // from/to doesn't metter because getRange is mocked
+        to: null
+      })
+      const editor = {
+        getRange () {
+          return 'house.name'
         }
-        },
-        getCursor: sinon.stub()
       }
 
       const hints = getHints(editor, {})
@@ -160,15 +182,11 @@ describe('hint.js', () => {
       { text: 'SELECT' },
       { text: 'ST' }
     ]
-    sinon.stub(CM.hint, 'sql').returns({ list })
+    sinon.stub(CM.hint, 'sql').returns({ list, from: null, to: null })
     const editor = {
-      getTokenAt () {
-        return {
-          string: 'se',
-          type: 'keyword'
+      getRange () {
+        return 'se'
       }
-      },
-      getCursor: sinon.stub()
     }
 
     const hints = getHints(editor, {})
@@ -182,15 +200,11 @@ describe('hint.js', () => {
     () => {
       // mock CM.hint.sql and editor
       const list = [{ text: 'SELECT' }]
-      sinon.stub(CM.hint, 'sql').returns({ list })
+      sinon.stub(CM.hint, 'sql').returns({ list, from: null, to: null })
       const editor = {
-        getTokenAt () {
-          return {
-            string: 'sele',
-            type: 'keyword'
+        getRange () {
+          return 'sele'
         }
-        },
-        getCursor: sinon.stub()
       }
 
       const hints = getHints(editor, {})