feat: add sitemap entry and options

src/main/java/run/halo/sitemap/SitemapEntry.java

@@ -0,0 +1,26 @@
+package run.halo.sitemap;
+
+import lombok.Builder;
+import lombok.Data;
+import lombok.NonNull;
+
+/**
+ * @author guqing
+ * @since 1.0.0
+ */
+@Data
+@Builder
+public class SitemapEntry {
+    /**
+     * <p>Parent tag for each URL entry. The remaining tags are children of this tag.</p>
+     * required.
+     */
+    @NonNull
+    private String loc;
+
+    private String lastmod;
+
+    private ChangeFreqEnum changefreq;
+
+    private Double priority;
+}

src/main/java/run/halo/sitemap/SitemapGeneratorOptions.java

@@ -0,0 +1,113 @@
+package run.halo.sitemap;
+
+import java.net.URI;
+import java.net.URISyntaxException;
+import java.net.URL;
+import java.nio.charset.StandardCharsets;
+import java.time.Instant;
+import java.time.format.DateTimeFormatter;
+import java.util.Set;
+import lombok.Builder;
+import lombok.Data;
+import lombok.NonNull;
+import org.apache.commons.lang3.StringUtils;
+import org.springframework.web.util.UriUtils;
+import run.halo.app.infra.utils.PathUtils;
+
+/**
+ * Sitemap generator options.
+ *
+ * @author guqing
+ * @since 1.0.0
+ */
+@Data
+@Builder
+public class SitemapGeneratorOptions {
+    /**
+     * All URLs in the generated sitemap(s) should appear under this base URL
+     */
+    @NonNull
+    private URL siteUrl;
+
+    @Builder.Default
+    private String fileNamePrefix = "sitemap";
+
+    @Builder.Default
+    private boolean allowEmptySitemap = false;
+
+    @Builder.Default
+    private boolean allowMultipleSitemaps = true;
+
+    @Builder.Default
+    private DateTimeFormatter dateTimeFormatter = W3cDatetimeFormat.MILLISECOND_FORMATTER;
+
+    /**
+     * Split large sitemap into multiple files by specifying sitemap size. Default 5000.
+     */
+    @Builder.Default
+    private int sitemapSize = 5000;
+
+    @Builder.Default
+    private boolean autoValidate = false;
+
+    @Builder.Default
+    private boolean gzip = false;
+
+    @Builder.Default
+    private ChangeFreqEnum changefreq = ChangeFreqEnum.DAILY;
+
+    @Builder.Default
+    private double priority = 0.7;
+
+    /**
+     * Add <lastmod/> property. Default true
+     */
+    @Builder.Default
+    private boolean autoLastmod = true;
+
+    /**
+     * <p>Array of relative paths (wildcard pattern supported) to exclude from listing on sitemap
+     * .xml or sitemap-*.xml.</p>
+     *
+     * <p>e.g.: ['/page-0', '/page-*', '/private/*'].</p>
+     * Apart from this option next-sitemap also offers a custom transform option which could be
+     * used to exclude urls that match specific patterns
+     */
+    private Set<String> exclude;
+
+    /**
+     * Generate index sitemaps. Default true.
+     */
+    @Builder.Default
+    private boolean generateIndexSitemap = true;
+
+    public SitemapEntry transform(String url) {
+        if (StringUtils.isBlank(url)) {
+            return null;
+        }
+        String escapedUrl = UrlUtils.escapeSitemapUrl(url);
+        String loc = UrlUtils.toURI(escapedUrl).normalize().toASCIIString();
+        if (!PathUtils.isAbsoluteUri(loc)) {
+            loc = getSiteUri().resolve(escapedUrl).normalize().toASCIIString();
+        }
+
+        SitemapEntry.SitemapEntryBuilder builder = SitemapEntry.builder()
+            .loc(loc)
+            .changefreq(changefreq)
+            .priority(priority);
+
+        if (dateTimeFormatter != null && autoLastmod) {
+            builder.lastmod(W3cDatetimeFormat.format(Instant.now(), dateTimeFormatter));
+        }
+        return builder.build();
+    }
+
+
+    private URI getSiteUri() {
+        try {
+            return siteUrl.toURI();
+        } catch (URISyntaxException e) {
+            throw new RuntimeException(e);
+        }
+    }
+}

src/main/java/run/halo/sitemap/UrlUtils.java

@@ -0,0 +1,40 @@
+package run.halo.sitemap;
+
+import java.net.URI;
+import java.net.URISyntaxException;
+import lombok.experimental.UtilityClass;
+import org.springframework.util.Assert;
+
+/**
+ * @author guqing
+ * @since 1.0.0
+ */
+@UtilityClass
+public final class UrlUtils {
+
+    /**
+     * <p>Your Sitemap file must be UTF-8 encoded (you can generally do this when you save the
+     * file).</p>
+     * As with all XML files, any data values (including URLs) must use entity escape codes for
+     * the characters listed in the table below.
+     */
+    public static String escapeSitemapUrl(String url) {
+        Assert.notNull(url, "The url must not be null");
+        return url.replaceAll("&", "&amp;")
+            .replaceAll("'", "&apos;")
+            .replaceAll("\"", "&quot;")
+            .replaceAll(">", "&gt;")
+            .replaceAll("<", "&lt;");
+    }
+
+    public static URI toURI(String s) {
+        if (s == null) {
+            return null;
+        }
+        try {
+            return new URI(escapeSitemapUrl(s));
+        } catch (URISyntaxException e) {
+            throw new RuntimeException(e);
+        }
+    }
+}

src/main/java/run/halo/sitemap/W3cDatetimeFormat.java

@@ -0,0 +1,79 @@
+package run.halo.sitemap;
+
+import java.time.Instant;
+import java.time.ZoneId;
+import java.time.format.DateTimeFormatter;
+import lombok.experimental.UtilityClass;
+
+/**
+ * Different standards may need different levels of granularity in the date and time, so this
+ * profile defines six levels. Standards that reference this profile should specify one or more
+ * of these granularities. If a given standard allows more than one granularity, it should
+ * specify the meaning of the dates and times with reduced precision, for example, the result of
+ * comparing two dates with different precisions.
+ * <p>
+ * The formats are as follows. Exactly the components shown here must be present, with exactly
+ * this punctuation. Note that the "T" appears literally in the string, to indicate the beginning
+ * of the time element, as specified in ISO 8601.
+ * <p>
+ * Year:
+ * YYYY (eg 1997)
+ * Year and month:
+ * YYYY-MM (eg 1997-07)
+ * Complete date:
+ * YYYY-MM-DD (eg 1997-07-16)
+ * Complete date plus hours and minutes:
+ * YYYY-MM-DDThh:mmTZD (eg 1997-07-16T19:20+01:00)
+ * Complete date plus hours, minutes and seconds:
+ * YYYY-MM-DDThh:mm:ssTZD (eg 1997-07-16T19:20:30+01:00)
+ * Complete date plus hours, minutes, seconds and a decimal fraction of a
+ * second
+ * YYYY-MM-DDThh:mm:ss.sTZD (eg 1997-07-16T19:20:30.45+01:00)
+ * where:
+ * <p>
+ * YYYY = four-digit year
+ * MM   = two-digit month (01=January, etc.)
+ * DD   = two-digit day of month (01 through 31)
+ * hh   = two digits of hour (00 through 23) (am/pm NOT allowed)
+ * mm   = two digits of minute (00 through 59)
+ * ss   = two digits of second (00 through 59)
+ * s    = one or more digits representing a decimal fraction of a second
+ * TZD  = time zone designator (Z or +hh:mm or -hh:mm)
+ * This profile does not specify how many digits may be used to represent the decimal fraction of
+ * a second. An adopting standard that permits fractions of a second must specify both the
+ * minimum number of digits (a number greater than or equal to one) and the maximum number of
+ * digits (the maximum may be stated to be "unlimited").
+ * <p>
+ * This profile defines two ways of handling time zone offsets:
+ * <p>
+ * Times are expressed in UTC (Coordinated Universal Time), with a special UTC designator ("Z").
+ * Times are expressed in local time, together with a time zone offset in hours and minutes. A
+ * time zone offset of "+hh:mm" indicates that the date/time uses a local time zone which is "hh"
+ * hours and "mm" minutes ahead of UTC. A time zone offset of "-hh:mm" indicates that the
+ * date/time uses a local time zone which is "hh" hours and "mm" minutes behind UTC.
+ * A standard referencing this profile should permit one or both of these ways of handling time
+ * zone offsets.
+ *
+ * @author guqing
+ * @since 1.0.0
+ */
+@UtilityClass
+public final class W3cDatetimeFormat {
+    public static final DateTimeFormatter MILLISECOND_FORMATTER =
+        DateTimeFormatter.ofPattern("yyyy-MM-dd'T'HH:mm:ss.SSSZ");
+
+    public static final DateTimeFormatter SECOND_FORMATTER =
+        DateTimeFormatter.ofPattern("yyyy-MM-dd'T'HH:mm:ssZ");
+
+    public static final DateTimeFormatter MINUTE_FORMATTER =
+        DateTimeFormatter.ofPattern("yyyy-MM-dd'T'HH:mmZ");
+
+    public static String format(Instant instant, DateTimeFormatter formatter) {
+        return instant.atZone(ZoneId.systemDefault())
+            .format(formatter.withZone(ZoneId.systemDefault()));
+    }
+
+    public static String format(Instant instant) {
+        return format(instant, MILLISECOND_FORMATTER);
+    }
+}