feat: export SuperMemo format with frequency ranking order

Directory.Packages.props

@@ -98,6 +98,7 @@
     <PackageVersion Include="Google.Protobuf" Version="3.21.10" />
     <PackageVersion Include="HtmlAgilityPack" Version="1.11.46" />
     <PackageVersion Include="Itc4net" Version="1.2.1" />
+    <PackageVersion Include="LemmaGenerator" Version="1.1.0" />
     <PackageVersion Include="Microsoft.Playwright" Version="1.28.0" />
     <PackageVersion Include="Newtonsoft.Json" Version="13.0.2" />
     <PackageVersion Include="Nito.Guids" Version="1.1.1" />

srcs/private/OxfordDictExtractor/ParserModel/CefrLevel.cs → srcs/private/OxfordDictExtractor/Core/CefrLevel.cs

@@ -16,11 +16,11 @@
 // You should have received a copy of the GNU General Public License along with
 // OneDotNet. If not, see <https://www.gnu.org/licenses/>.
 
-namespace OxfordDictExtractor.ParserModel
+namespace OxfordDictExtractor.Core
 {
     public enum CefrLevel
     {
-        Unspecified,
+        Unspecified = 0,
         A1,
         A2,
         B1,

srcs/private/OxfordDictExtractor/Core/CocaWordFrequencyLemmaEntry.cs

@@ -0,0 +1,31 @@
+// Copyright (c) 2022 Zhang Shuai<[email protected]>.
+// All rights reserved.
+//
+// This file is part of OneDotNet.
+//
+// OneDotNet is free software: you can redistribute it and/or modify it under
+// the terms of the GNU General Public License as published by the Free
+// Software Foundation, either version 3 of the License, or (at your option)
+// any later version.
+//
+// OneDotNet is distributed in the hope that it will be useful, but WITHOUT ANY
+// WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
+// FOR A PARTICULAR PURPOSE. See the GNU General Public License for more
+// details.
+//
+// You should have received a copy of the GNU General Public License along with
+// OneDotNet. If not, see <https://www.gnu.org/licenses/>.
+
+namespace OxfordDictExtractor.Core
+{
+    // See https://www.wordfrequency.info/files.asp
+    // Rank: 1-62,000. Based on word frequency.
+    // Lemma: Again, the "dictionary / headword" entry. This is why was or happier or shoes would
+    //        not be included here; they are word forms of the lemmas be, happy, and shoe.
+    // PoS: Part of speech. This is the first letter of the codes from https://ucrel.lancs.ac.uk/claws7tags.html
+    //      (e.g. N for noun, V for verb, A for adjective, R for adverb, P for preposition, C for conjunction,
+    //      D for determiner, I for interjection, M for numeral, U for pronoun, X for other).
+    internal record CocaWordFrequencyLemmaEntry(int Rank, string Lemma, string PoS)
+    {
+    }
+}

srcs/private/OxfordDictExtractor/Core/OxfordWordListEntry.cs

@@ -0,0 +1,24 @@
+// Copyright (c) 2022 Zhang Shuai<[email protected]>.
+// All rights reserved.
+//
+// This file is part of OneDotNet.
+//
+// OneDotNet is free software: you can redistribute it and/or modify it under
+// the terms of the GNU General Public License as published by the Free
+// Software Foundation, either version 3 of the License, or (at your option)
+// any later version.
+//
+// OneDotNet is distributed in the hope that it will be useful, but WITHOUT ANY
+// WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
+// FOR A PARTICULAR PURPOSE. See the GNU General Public License for more
+// details.
+//
+// You should have received a copy of the GNU General Public License along with
+// OneDotNet. If not, see <https://www.gnu.org/licenses/>.
+
+namespace OxfordDictExtractor.Core
+{
+    internal record OxfordWordListEntry(string Key, CefrLevel Oxford3000CefrLevel, CefrLevel Oxford5000CefrLevel)
+    {
+    }
+}

srcs/private/OxfordDictExtractor/Data/README.md

@@ -0,0 +1,35 @@
+# Data
+
+## wordlist.tsv.zip
+
+Extracted from OALD mdx files.
+
+The dictionary file is from https://pdawiki.com/forum/thread-38955-1-1.html (v13.2)
+
+The Chinese meanings are coming from OALD9 official version, but the newly added
+terms are machine translated.
+
+Extracted by https://github.com/liuyug/mdict-utils to SQLite database, and then
+exported to TSV file.
+
+## lemmas.csv
+
+Downloaded from https://www.wordfrequency.info/samples.asp.
+
+Top 60,000 "lemmas" -> Top 5000 -> Download -> Open with Excel & Save as CSV.
+
+It's possibly too small. Maybe I'd consider some unknown time table.
+
+https://raw.githubusercontent.com/whatofit/LevelWordWithFreq/master/src/main/resources/%E7%BE%8E%E5%9B%BD%E5%BD%93%E4%BB%A3%E8%8B%B1%E8%AF%AD%E8%AF%AD%E6%96%99%E5%BA%93COCA%E8%AF%8D%E9%A2%9120000_words_unique.txt
+
+## oxford3000-5000.html & oxford-phrase-list.html
+
+Wordlist downloaded from https://www.oxfordlearnersdictionaries.com/wordlists/oxford3000-5000.
+
+Phase list downloaded from https://www.oxfordlearnersdictionaries.com/wordlists/oxford-phrase-list.
+
+## full7z-mlteast-en.lem
+
+Downloaded from https://github.com/AlexPoint/LemmaGenerator/blob/05f6883970dc863d61c52e169d1e016fa5c8d67b/Test/Data/Custom/full7z-mlteast-en-modified.lem.
+
+Use this file due to issue https://github.com/AlexPoint/LemmaGenerator/issues/2.

srcs/private/OxfordDictExtractor/Data/Update-OxfordPhraseList.ps1

@@ -0,0 +1,8 @@
+Invoke-WebRequest `
+  -UseBasicParsing `
+  -Uri "https://www.oxfordlearnersdictionaries.com/wordlists/oxford-phrase-list" `
+  -TimeoutSec 5 `
+  -MaximumRetryCount 3 `
+  -RetryIntervalSec 1 `
+  -Method GET `
+  -OutFile "${PSScriptRoot}\oxford-phrase-list.$([DateTimeOffset]::UtcNow.ToString("yyyyMMdd'T'HHmmssZ", [cultureinfo]::InvariantCulture)).html"

srcs/private/OxfordDictExtractor/Data/Update-OxfordWordlists.ps1

@@ -0,0 +1,8 @@
+Invoke-WebRequest `
+  -UseBasicParsing `
+  -Uri "https://www.oxfordlearnersdictionaries.com/wordlists/oxford3000-5000" `
+  -TimeoutSec 5 `
+  -MaximumRetryCount 3 `
+  -RetryIntervalSec 1 `
+  -Method GET `
+  -OutFile "${PSScriptRoot}\oxford3000-5000.$([DateTimeOffset]::UtcNow.ToString("yyyyMMdd'T'HHmmssZ", [cultureinfo]::InvariantCulture)).html"