From 264bfe4115c3950c062b7aa2eeb31f92b8ad689a Mon Sep 17 00:00:00 2001 From: "Collin M. Barrett" Date: Thu, 30 Aug 2018 18:02:21 -0500 Subject: [PATCH] skip storing snapshot on matching checksum closes #349 --- .../20180830220606_AddMd5Checksum.Designer.cs | 643 ++++++++++++++++++ .../20180830220606_AddMd5Checksum.cs | 23 + .../FilterListsDbContextModelSnapshot.cs | 3 + src/FilterLists.Data/Entities/Snapshot.cs | 3 +- .../SnapshotTypeConfiguration.cs | 2 + src/FilterLists.Services/Snapshot/Snapshot.cs | 55 +- 6 files changed, 714 insertions(+), 15 deletions(-) create mode 100644 src/FilterLists.Api/Migrations/20180830220606_AddMd5Checksum.Designer.cs create mode 100644 src/FilterLists.Api/Migrations/20180830220606_AddMd5Checksum.cs diff --git a/src/FilterLists.Api/Migrations/20180830220606_AddMd5Checksum.Designer.cs b/src/FilterLists.Api/Migrations/20180830220606_AddMd5Checksum.Designer.cs new file mode 100644 index 000000000..be75a8b37 --- /dev/null +++ b/src/FilterLists.Api/Migrations/20180830220606_AddMd5Checksum.Designer.cs @@ -0,0 +1,643 @@ +// + +using System; +using FilterLists.Data; +using Microsoft.EntityFrameworkCore; +using Microsoft.EntityFrameworkCore.Infrastructure; +using Microsoft.EntityFrameworkCore.Metadata; +using Microsoft.EntityFrameworkCore.Migrations; + +namespace FilterLists.Api.Migrations +{ + [DbContext(typeof(FilterListsDbContext))] + [Migration("20180830220606_AddMd5Checksum")] + partial class AddMd5Checksum + { + protected override void BuildTargetModel(ModelBuilder modelBuilder) + { +#pragma warning disable 612, 618 + modelBuilder + .HasAnnotation("ProductVersion", "2.1.2-rtm-30932") + .HasAnnotation("Relational:MaxIdentifierLength", 64); + + modelBuilder.Entity("FilterLists.Data.Entities.FilterList", b => + { + b.Property("Id") + .ValueGeneratedOnAdd() + .HasColumnType("SMALLINT UNSIGNED") + .HasAnnotation("MySql:ValueGenerationStrategy", MySqlValueGenerationStrategy.IdentityColumn); + + b.Property("ChatUrl") + .HasColumnType("TEXT"); + + b.Property("CreatedDateUtc") + .IsRequired() + .ValueGeneratedOnAdd() + .HasColumnType("TIMESTAMP") + .HasDefaultValueSql("current_timestamp()"); + + b.Property("Description") + .HasColumnType("TEXT"); + + b.Property("DescriptionSourceUrl") + .HasColumnType("TEXT"); + + b.Property("DiscontinuedDate") + .ValueGeneratedOnAdd() + .HasColumnType("DATE") + .HasDefaultValueSql("NULL"); + + b.Property("DonateUrl") + .HasColumnType("TEXT"); + + b.Property("EmailAddress") + .ValueGeneratedOnAdd() + .HasColumnType("VARCHAR(126)") + .HasDefaultValueSql("NULL"); + + b.Property("ForumUrl") + .HasColumnType("TEXT"); + + b.Property("HomeUrl") + .HasColumnType("TEXT"); + + b.Property("IssuesUrl") + .HasColumnType("TEXT"); + + b.Property("LicenseId") + .ValueGeneratedOnAdd() + .HasDefaultValue((byte)5); + + b.Property("ModifiedDateUtc") + .IsRequired() + .ValueGeneratedOnAddOrUpdate() + .HasColumnType("TIMESTAMP") + .HasDefaultValueSql("current_timestamp() ON UPDATE current_timestamp()"); + + b.Property("Name") + .IsRequired() + .HasColumnType("VARCHAR(126)"); + + b.Property("PolicyUrl") + .HasColumnType("TEXT"); + + b.Property("PublishedDate") + .ValueGeneratedOnAdd() + .HasColumnType("DATE") + .HasDefaultValueSql("NULL"); + + b.Property("SubmissionUrl") + .HasColumnType("TEXT"); + + b.Property("SyntaxId"); + + b.Property("ViewUrl") + .HasColumnType("TEXT"); + + b.HasKey("Id"); + + b.HasIndex("LicenseId"); + + b.HasIndex("SyntaxId"); + + b.ToTable("filterlists"); + }); + + modelBuilder.Entity("FilterLists.Data.Entities.Junctions.FilterListLanguage", b => + { + b.Property("FilterListId"); + + b.Property("LanguageId"); + + b.Property("CreatedDateUtc") + .IsRequired() + .ValueGeneratedOnAdd() + .HasColumnType("TIMESTAMP") + .HasDefaultValueSql("current_timestamp()"); + + b.HasKey("FilterListId", "LanguageId"); + + b.HasIndex("LanguageId"); + + b.ToTable("filterlists_languages"); + }); + + modelBuilder.Entity("FilterLists.Data.Entities.Junctions.FilterListMaintainer", b => + { + b.Property("FilterListId"); + + b.Property("MaintainerId"); + + b.Property("CreatedDateUtc") + .IsRequired() + .ValueGeneratedOnAdd() + .HasColumnType("TIMESTAMP") + .HasDefaultValueSql("current_timestamp()"); + + b.HasKey("FilterListId", "MaintainerId"); + + b.HasIndex("MaintainerId"); + + b.ToTable("filterlists_maintainers"); + }); + + modelBuilder.Entity("FilterLists.Data.Entities.Junctions.FilterListTag", b => + { + b.Property("FilterListId"); + + b.Property("TagId"); + + b.Property("CreatedDateUtc") + .IsRequired() + .ValueGeneratedOnAdd() + .HasColumnType("TIMESTAMP") + .HasDefaultValueSql("current_timestamp()"); + + b.HasKey("FilterListId", "TagId"); + + b.HasIndex("TagId"); + + b.ToTable("filterlists_tags"); + }); + + modelBuilder.Entity("FilterLists.Data.Entities.Junctions.Fork", b => + { + b.Property("ForkFilterListId"); + + b.Property("UpstreamFilterListId"); + + b.Property("CreatedDateUtc") + .IsRequired() + .ValueGeneratedOnAdd() + .HasColumnType("TIMESTAMP") + .HasDefaultValueSql("current_timestamp()"); + + b.HasKey("ForkFilterListId", "UpstreamFilterListId"); + + b.HasIndex("UpstreamFilterListId"); + + b.ToTable("forks"); + }); + + modelBuilder.Entity("FilterLists.Data.Entities.Junctions.Merge", b => + { + b.Property("MergeFilterListId"); + + b.Property("UpstreamFilterListId"); + + b.Property("CreatedDateUtc") + .IsRequired() + .ValueGeneratedOnAdd() + .HasColumnType("TIMESTAMP") + .HasDefaultValueSql("current_timestamp()"); + + b.HasKey("MergeFilterListId", "UpstreamFilterListId"); + + b.HasIndex("UpstreamFilterListId"); + + b.ToTable("merges"); + }); + + modelBuilder.Entity("FilterLists.Data.Entities.Junctions.SnapshotRule", b => + { + b.Property("SnapshotId"); + + b.Property("RuleId"); + + b.HasKey("SnapshotId", "RuleId"); + + b.HasIndex("RuleId"); + + b.ToTable("snapshots_rules"); + }); + + modelBuilder.Entity("FilterLists.Data.Entities.Junctions.SoftwareSyntax", b => + { + b.Property("SyntaxId"); + + b.Property("SoftwareId"); + + b.Property("CreatedDateUtc") + .IsRequired() + .ValueGeneratedOnAdd() + .HasColumnType("TIMESTAMP") + .HasDefaultValueSql("current_timestamp()"); + + b.HasKey("SyntaxId", "SoftwareId"); + + b.HasIndex("SoftwareId"); + + b.ToTable("software_syntaxes"); + }); + + modelBuilder.Entity("FilterLists.Data.Entities.Language", b => + { + b.Property("Id") + .ValueGeneratedOnAdd() + .HasColumnType("SMALLINT UNSIGNED") + .HasAnnotation("MySql:ValueGenerationStrategy", MySqlValueGenerationStrategy.IdentityColumn); + + b.Property("CreatedDateUtc") + .IsRequired() + .ValueGeneratedOnAdd() + .HasColumnType("TIMESTAMP") + .HasDefaultValueSql("current_timestamp()"); + + b.Property("Iso6391") + .ValueGeneratedOnAdd() + .HasColumnType("VARCHAR(2)") + .HasDefaultValueSql("NULL"); + + b.Property("Iso6392") + .ValueGeneratedOnAdd() + .HasColumnType("VARCHAR(3)") + .HasDefaultValueSql("NULL"); + + b.Property("Iso6392B") + .ValueGeneratedOnAdd() + .HasColumnType("VARCHAR(3)") + .HasDefaultValueSql("NULL"); + + b.Property("Iso6392T") + .ValueGeneratedOnAdd() + .HasColumnType("VARCHAR(3)") + .HasDefaultValueSql("NULL"); + + b.Property("Iso6393") + .ValueGeneratedOnAdd() + .HasColumnType("VARCHAR(3)") + .HasDefaultValueSql("NULL"); + + b.Property("LocalName") + .ValueGeneratedOnAdd() + .HasColumnType("VARCHAR(126)") + .HasDefaultValueSql("NULL"); + + b.Property("ModifiedDateUtc") + .IsRequired() + .ValueGeneratedOnAddOrUpdate() + .HasColumnType("TIMESTAMP") + .HasDefaultValueSql("current_timestamp() ON UPDATE current_timestamp()"); + + b.Property("Name") + .ValueGeneratedOnAdd() + .HasColumnType("VARCHAR(126)") + .HasDefaultValueSql("NULL"); + + b.HasKey("Id"); + + b.ToTable("languages"); + }); + + modelBuilder.Entity("FilterLists.Data.Entities.License", b => + { + b.Property("Id") + .ValueGeneratedOnAdd() + .HasColumnType("TINYINT UNSIGNED") + .HasAnnotation("MySql:ValueGenerationStrategy", MySqlValueGenerationStrategy.IdentityColumn); + + b.Property("CreatedDateUtc") + .IsRequired() + .ValueGeneratedOnAdd() + .HasColumnType("TIMESTAMP") + .HasDefaultValueSql("current_timestamp()"); + + b.Property("DescriptionUrl") + .HasColumnType("TEXT"); + + b.Property("ModifiedDateUtc") + .IsRequired() + .ValueGeneratedOnAddOrUpdate() + .HasColumnType("TIMESTAMP") + .HasDefaultValueSql("current_timestamp() ON UPDATE current_timestamp()"); + + b.Property("Name") + .IsRequired() + .HasColumnType("VARCHAR(126)"); + + b.Property("PermissiveAdaptation"); + + b.Property("PermissiveCommercial"); + + b.HasKey("Id"); + + b.ToTable("licenses"); + }); + + modelBuilder.Entity("FilterLists.Data.Entities.Maintainer", b => + { + b.Property("Id") + .ValueGeneratedOnAdd() + .HasColumnType("SMALLINT UNSIGNED") + .HasAnnotation("MySql:ValueGenerationStrategy", MySqlValueGenerationStrategy.IdentityColumn); + + b.Property("CreatedDateUtc") + .IsRequired() + .ValueGeneratedOnAdd() + .HasColumnType("TIMESTAMP") + .HasDefaultValueSql("current_timestamp()"); + + b.Property("EmailAddress") + .ValueGeneratedOnAdd() + .HasColumnType("VARCHAR(126)") + .HasDefaultValueSql("NULL"); + + b.Property("HomeUrl") + .HasColumnType("TEXT"); + + b.Property("ModifiedDateUtc") + .IsRequired() + .ValueGeneratedOnAddOrUpdate() + .HasColumnType("TIMESTAMP") + .HasDefaultValueSql("current_timestamp() ON UPDATE current_timestamp()"); + + b.Property("Name") + .IsRequired() + .HasColumnType("VARCHAR(126)"); + + b.Property("TwitterHandle") + .ValueGeneratedOnAdd() + .HasColumnType("VARCHAR(126)") + .HasDefaultValueSql("NULL"); + + b.HasKey("Id"); + + b.ToTable("maintainers"); + }); + + modelBuilder.Entity("FilterLists.Data.Entities.Rule", b => + { + b.Property("Id") + .ValueGeneratedOnAdd() + .HasColumnType("INT UNSIGNED") + .HasAnnotation("MySql:ValueGenerationStrategy", MySqlValueGenerationStrategy.IdentityColumn); + + b.Property("CreatedDateUtc") + .IsRequired() + .ValueGeneratedOnAdd() + .HasColumnType("TIMESTAMP") + .HasDefaultValueSql("current_timestamp()"); + + b.Property("Raw") + .IsRequired() + .HasColumnType("LONGTEXT"); + + b.HasKey("Id"); + + b.ToTable("rules"); + }); + + modelBuilder.Entity("FilterLists.Data.Entities.Snapshot", b => + { + b.Property("Id") + .ValueGeneratedOnAdd() + .HasColumnType("MEDIUMINT UNSIGNED") + .HasAnnotation("MySql:ValueGenerationStrategy", MySqlValueGenerationStrategy.IdentityColumn); + + b.Property("CreatedDateUtc") + .IsRequired() + .ValueGeneratedOnAdd() + .HasColumnType("TIMESTAMP") + .HasDefaultValueSql("current_timestamp()"); + + b.Property("FilterListId"); + + b.Property("HttpStatusCode") + .ValueGeneratedOnAdd() + .HasColumnType("SMALLINT") + .HasDefaultValueSql("NULL"); + + b.Property("Md5Checksum") + .HasColumnType("BINARY(16)"); + + b.Property("ModifiedDateUtc") + .IsRequired() + .ValueGeneratedOnAddOrUpdate() + .HasColumnType("TIMESTAMP") + .HasDefaultValueSql("current_timestamp() ON UPDATE current_timestamp()"); + + b.Property("WasSuccessful"); + + b.Property("WaybackTimestamp") + .HasColumnType("TIMESTAMP"); + + b.Property("WaybackUrl") + .HasColumnType("TEXT"); + + b.HasKey("Id"); + + b.HasIndex("FilterListId"); + + b.ToTable("snapshots"); + }); + + modelBuilder.Entity("FilterLists.Data.Entities.Software", b => + { + b.Property("Id") + .ValueGeneratedOnAdd() + .HasColumnType("TINYINT UNSIGNED") + .HasAnnotation("MySql:ValueGenerationStrategy", MySqlValueGenerationStrategy.IdentityColumn); + + b.Property("CreatedDateUtc") + .IsRequired() + .ValueGeneratedOnAdd() + .HasColumnType("TIMESTAMP") + .HasDefaultValueSql("current_timestamp()"); + + b.Property("DownloadUrl") + .HasColumnType("TEXT"); + + b.Property("HomeUrl") + .HasColumnType("TEXT"); + + b.Property("ModifiedDateUtc") + .IsRequired() + .ValueGeneratedOnAddOrUpdate() + .HasColumnType("TIMESTAMP") + .HasDefaultValueSql("current_timestamp() ON UPDATE current_timestamp()"); + + b.Property("Name") + .IsRequired() + .HasColumnType("VARCHAR(126)"); + + b.HasKey("Id"); + + b.ToTable("software"); + }); + + modelBuilder.Entity("FilterLists.Data.Entities.Syntax", b => + { + b.Property("Id") + .ValueGeneratedOnAdd() + .HasColumnType("TINYINT UNSIGNED") + .HasAnnotation("MySql:ValueGenerationStrategy", MySqlValueGenerationStrategy.IdentityColumn); + + b.Property("CreatedDateUtc") + .IsRequired() + .ValueGeneratedOnAdd() + .HasColumnType("TIMESTAMP") + .HasDefaultValueSql("current_timestamp()"); + + b.Property("DefinitionUrl") + .HasColumnType("TEXT"); + + b.Property("ModifiedDateUtc") + .IsRequired() + .ValueGeneratedOnAddOrUpdate() + .HasColumnType("TIMESTAMP") + .HasDefaultValueSql("current_timestamp() ON UPDATE current_timestamp()"); + + b.Property("Name") + .IsRequired() + .HasColumnType("VARCHAR(126)"); + + b.HasKey("Id"); + + b.ToTable("syntaxes"); + }); + + modelBuilder.Entity("FilterLists.Data.Entities.Tag", b => + { + b.Property("Id") + .ValueGeneratedOnAdd() + .HasColumnType("TINYINT UNSIGNED") + .HasAnnotation("MySql:ValueGenerationStrategy", MySqlValueGenerationStrategy.IdentityColumn); + + b.Property("CreatedDateUtc") + .IsRequired() + .ValueGeneratedOnAdd() + .HasColumnType("TIMESTAMP") + .HasDefaultValueSql("current_timestamp()"); + + b.Property("Description") + .HasColumnType("TEXT"); + + b.Property("ModifiedDateUtc") + .IsRequired() + .ValueGeneratedOnAddOrUpdate() + .HasColumnType("TIMESTAMP") + .HasDefaultValueSql("current_timestamp() ON UPDATE current_timestamp()"); + + b.Property("Name") + .IsRequired() + .HasColumnType("VARCHAR(126)"); + + b.HasKey("Id"); + + b.ToTable("tags"); + }); + + modelBuilder.Entity("FilterLists.Data.Entities.FilterList", b => + { + b.HasOne("FilterLists.Data.Entities.License", "License") + .WithMany("FilterLists") + .HasForeignKey("LicenseId") + .OnDelete(DeleteBehavior.Cascade); + + b.HasOne("FilterLists.Data.Entities.Syntax", "Syntax") + .WithMany("FilterLists") + .HasForeignKey("SyntaxId"); + }); + + modelBuilder.Entity("FilterLists.Data.Entities.Junctions.FilterListLanguage", b => + { + b.HasOne("FilterLists.Data.Entities.FilterList", "FilterList") + .WithMany("FilterListLanguages") + .HasForeignKey("FilterListId") + .OnDelete(DeleteBehavior.Cascade); + + b.HasOne("FilterLists.Data.Entities.Language", "Language") + .WithMany("FilterListLanguages") + .HasForeignKey("LanguageId") + .OnDelete(DeleteBehavior.Cascade); + }); + + modelBuilder.Entity("FilterLists.Data.Entities.Junctions.FilterListMaintainer", b => + { + b.HasOne("FilterLists.Data.Entities.FilterList", "FilterList") + .WithMany("FilterListMaintainers") + .HasForeignKey("FilterListId") + .OnDelete(DeleteBehavior.Cascade); + + b.HasOne("FilterLists.Data.Entities.Maintainer", "Maintainer") + .WithMany("FilterListMaintainers") + .HasForeignKey("MaintainerId") + .OnDelete(DeleteBehavior.Cascade); + }); + + modelBuilder.Entity("FilterLists.Data.Entities.Junctions.FilterListTag", b => + { + b.HasOne("FilterLists.Data.Entities.FilterList", "FilterList") + .WithMany("FilterListTags") + .HasForeignKey("FilterListId") + .OnDelete(DeleteBehavior.Cascade); + + b.HasOne("FilterLists.Data.Entities.Tag", "Tag") + .WithMany("FilterListTags") + .HasForeignKey("TagId") + .OnDelete(DeleteBehavior.Cascade); + }); + + modelBuilder.Entity("FilterLists.Data.Entities.Junctions.Fork", b => + { + b.HasOne("FilterLists.Data.Entities.FilterList", "ForkFilterList") + .WithMany("ForkFilterLists") + .HasForeignKey("ForkFilterListId") + .OnDelete(DeleteBehavior.Cascade); + + b.HasOne("FilterLists.Data.Entities.FilterList", "UpstreamFilterList") + .WithMany("UpstreamForkFilterLists") + .HasForeignKey("UpstreamFilterListId") + .OnDelete(DeleteBehavior.Cascade); + }); + + modelBuilder.Entity("FilterLists.Data.Entities.Junctions.Merge", b => + { + b.HasOne("FilterLists.Data.Entities.FilterList", "MergeFilterList") + .WithMany("MergeFilterLists") + .HasForeignKey("MergeFilterListId") + .OnDelete(DeleteBehavior.Cascade); + + b.HasOne("FilterLists.Data.Entities.FilterList", "UpstreamFilterList") + .WithMany("UpstreamMergeFilterLists") + .HasForeignKey("UpstreamFilterListId") + .OnDelete(DeleteBehavior.Cascade); + }); + + modelBuilder.Entity("FilterLists.Data.Entities.Junctions.SnapshotRule", b => + { + b.HasOne("FilterLists.Data.Entities.Rule", "Rule") + .WithMany("SnapshotRules") + .HasForeignKey("RuleId") + .OnDelete(DeleteBehavior.Cascade); + + b.HasOne("FilterLists.Data.Entities.Snapshot", "Snapshot") + .WithMany("SnapshotRules") + .HasForeignKey("SnapshotId") + .OnDelete(DeleteBehavior.Cascade); + }); + + modelBuilder.Entity("FilterLists.Data.Entities.Junctions.SoftwareSyntax", b => + { + b.HasOne("FilterLists.Data.Entities.Software", "Software") + .WithMany("SoftwareSyntaxes") + .HasForeignKey("SoftwareId") + .OnDelete(DeleteBehavior.Cascade); + + b.HasOne("FilterLists.Data.Entities.Syntax", "Syntax") + .WithMany("SoftwareSyntaxes") + .HasForeignKey("SyntaxId") + .OnDelete(DeleteBehavior.Cascade); + }); + + modelBuilder.Entity("FilterLists.Data.Entities.Snapshot", b => + { + b.HasOne("FilterLists.Data.Entities.FilterList", "FilterList") + .WithMany("Snapshots") + .HasForeignKey("FilterListId") + .OnDelete(DeleteBehavior.Cascade); + }); +#pragma warning restore 612, 618 + } + } +} \ No newline at end of file diff --git a/src/FilterLists.Api/Migrations/20180830220606_AddMd5Checksum.cs b/src/FilterLists.Api/Migrations/20180830220606_AddMd5Checksum.cs new file mode 100644 index 000000000..f5edafc81 --- /dev/null +++ b/src/FilterLists.Api/Migrations/20180830220606_AddMd5Checksum.cs @@ -0,0 +1,23 @@ +using Microsoft.EntityFrameworkCore.Migrations; + +namespace FilterLists.Api.Migrations +{ + public partial class AddMd5Checksum : Migration + { + protected override void Up(MigrationBuilder migrationBuilder) + { + migrationBuilder.AddColumn( + "Md5Checksum", + "snapshots", + "BINARY(16)", + nullable: true); + } + + protected override void Down(MigrationBuilder migrationBuilder) + { + migrationBuilder.DropColumn( + "Md5Checksum", + "snapshots"); + } + } +} \ No newline at end of file diff --git a/src/FilterLists.Api/Migrations/FilterListsDbContextModelSnapshot.cs b/src/FilterLists.Api/Migrations/FilterListsDbContextModelSnapshot.cs index 7263e6578..60824e763 100644 --- a/src/FilterLists.Api/Migrations/FilterListsDbContextModelSnapshot.cs +++ b/src/FilterLists.Api/Migrations/FilterListsDbContextModelSnapshot.cs @@ -405,6 +405,9 @@ protected override void BuildModel(ModelBuilder modelBuilder) .HasColumnType("SMALLINT") .HasDefaultValueSql("NULL"); + b.Property("Md5Checksum") + .HasColumnType("BINARY(16)"); + b.Property("ModifiedDateUtc") .IsRequired() .ValueGeneratedOnAddOrUpdate() diff --git a/src/FilterLists.Data/Entities/Snapshot.cs b/src/FilterLists.Data/Entities/Snapshot.cs index 7772e3689..ab0ebf1c6 100644 --- a/src/FilterLists.Data/Entities/Snapshot.cs +++ b/src/FilterLists.Data/Entities/Snapshot.cs @@ -9,8 +9,9 @@ public class Snapshot : BaseEntity public uint FilterListId { get; set; } public FilterList FilterList { get; set; } public int? HttpStatusCode { get; set; } - public bool WasSuccessful { get; set; } + public byte[] Md5Checksum { get; set; } public ICollection SnapshotRules { get; set; } + public bool WasSuccessful { get; set; } public DateTime? WaybackTimestamp { get; set; } public string WaybackUrl { get; set; } } diff --git a/src/FilterLists.Data/EntityTypeConfigurations/SnapshotTypeConfiguration.cs b/src/FilterLists.Data/EntityTypeConfigurations/SnapshotTypeConfiguration.cs index e44e38c85..34ae29b27 100644 --- a/src/FilterLists.Data/EntityTypeConfigurations/SnapshotTypeConfiguration.cs +++ b/src/FilterLists.Data/EntityTypeConfigurations/SnapshotTypeConfiguration.cs @@ -15,6 +15,8 @@ public override void Configure(EntityTypeBuilder entityTypeBuilder) entityTypeBuilder.Property(x => x.HttpStatusCode) .HasColumnType("SMALLINT") .HasDefaultValueSql("NULL"); + entityTypeBuilder.Property(x => x.Md5Checksum) + .HasColumnType("BINARY(16)"); entityTypeBuilder.Property(x => x.WaybackTimestamp) .HasColumnType("TIMESTAMP"); entityTypeBuilder.Property(x => x.WaybackUrl) diff --git a/src/FilterLists.Services/Snapshot/Snapshot.cs b/src/FilterLists.Services/Snapshot/Snapshot.cs index f2b59eab9..327f76726 100644 --- a/src/FilterLists.Services/Snapshot/Snapshot.cs +++ b/src/FilterLists.Services/Snapshot/Snapshot.cs @@ -4,6 +4,7 @@ using System.Linq; using System.Net; using System.Net.Http; +using System.Security.Cryptography; using System.Threading; using System.Threading.Tasks; using FilterLists.Data; @@ -12,6 +13,7 @@ using FilterLists.Services.Snapshot.Models; using JetBrains.Annotations; using Microsoft.ApplicationInsights; +using Microsoft.EntityFrameworkCore; using MoreLinq; using SharpCompress.Archives.SevenZip; @@ -112,27 +114,52 @@ private async Task GetLines() lines = new HashSet(); using (var stream = await response.Content.ReadAsStreamAsync()) { - if (ListUrl.EndsWith(".7z")) - await GetLinesFrom7Zip(stream); - else - await GetLinesFromStream(stream); + using (var memoryStream = new MemoryStream()) + { + await stream.CopyToAsync(memoryStream); + await SaveChecksum(memoryStream); + if (await IsNewChecksum()) + { + memoryStream.Position = 0; + if (ListUrl.EndsWith(".7z")) + await GetLinesFrom7Zip(memoryStream); + else + await GetLinesFromStream(memoryStream); + } + } } } } + private async Task SaveChecksum(Stream stream) + { + using (var md5 = MD5.Create()) + { + SnapEntity.Md5Checksum = md5.ComputeHash(stream); + } + + await dbContext.SaveChangesAsync(); + } + + private async Task IsNewChecksum() => + !SnapEntity.Md5Checksum.SequenceEqual(await GetPreviousChecksum() ?? Array.Empty()); + + private async Task GetPreviousChecksum() => + await dbContext.Snapshots + .Where(s => s.WasSuccessful && s.FilterListId == List.Id) + .OrderByDescending(s => s.CreatedDateUtc) + .Select(s => s.Md5Checksum) + .FirstOrDefaultAsync(); + private async Task GetLinesFrom7Zip(Stream stream) { - using (var memoryStream = new MemoryStream()) + using (var archive = SevenZipArchive.Open(stream)) { - stream.CopyTo(memoryStream); - using (var archive = SevenZipArchive.Open(memoryStream)) - { - foreach (var entry in archive.Entries.Where(entry => !entry.IsDirectory)) - using (var entryMemoryStream = entry.OpenEntryStream()) - { - await GetLinesFromStream(entryMemoryStream); - } - } + foreach (var entry in archive.Entries.Where(entry => !entry.IsDirectory)) + using (var entryMemoryStream = entry.OpenEntryStream()) + { + await GetLinesFromStream(entryMemoryStream); + } } }