Merge pull request #777 from clulab/date-rule-issue776

Date rule issue776

main/src/main/resources/org/clulab/numeric/WEEK.tsv

@@ -1,16 +1,18 @@
 #
 # list of weeks and their date ranges, case insensitive so everything is lower case for simplicity
-# the comments after // are required by WeekNormalizer to get the week date ranges! Do not remove
-# the format for the date ranges must be MM-dd:MM-dd or MM:MM
-# note: multi-word phrases must be tokenized in the same way as our tokenizer. If not sure, try the phrases in ./shell first!
+# the comments after // are required by WeekNormalizer to get the week date ranges! Do not remove.
+# The format for the date ranges must be MM-dd:MM-dd or MM:MM.
+# Note: multi-word phrases must be tokenized in the same way as our tokenizer. If not sure, try the
+# phrases in ./shell first!
 #
-first week       // XXXX-XX-01 -- XXXX-XX-07
-1st week       // XXXX-XX-01 -- XXXX-XX-07
-second week      // XXXX-XX-08 -- XXXX-XX-14
-2nd week      // XXXX-XX-08 -- XXXX-XX-14
-third week       // XXXX-XX-15 -- XXXX-XX-21
-3rd week       // XXXX-XX-15 -- XXXX-XX-21
-fourth week      // XXXX-XX-22 -- XXXX-XX-28
-4th week      // XXXX-XX-22 -- XXXX-XX-28
-first two weeks  // XXXX-XX-01 -- XXXX-XX-14
-second two weeks // XXXX-XX-15 -- XXXX-XX-28
+# Update: If the week (left column) includes a pipe (|), the "week" will be split into multiple
+# entries all having the same date range to the right.  Weeks will also be trimmed so that the
+# entries can be vertically aligned to assure that nothing has been forgotten.  Empty values between
+# || will also be removed.
+#
+ first week|            |1st week|         |first |1st      // XXXX-XX-01 -- XXXX-XX-07
+second week|second weeks|2nd week|2nd weeks|second|2nd      // XXXX-XX-08 -- XXXX-XX-14
+ third week| third weeks|3rd week|3rd weeks|third |3rd      // XXXX-XX-15 -- XXXX-XX-21
+fourth week|fourth weeks|4th week|4th weeks                 // XXXX-XX-22 -- XXXX-XX-28
+ first two weeks                                            // XXXX-XX-01 -- XXXX-XX-14
+second two weeks                                            // XXXX-XX-15 -- XXXX-XX-28

main/src/main/resources/org/clulab/numeric/date-ranges.yml

@@ -58,6 +58,15 @@
   pattern: |
     /(?i)between/ @month1:PossibleMonth /(?i)(and|to)/ @month2:PossibleMonth @year:PossibleYear
 
+- name: date-range-5-week
+  priority: ${rulepriority}
+  label: DateRange
+  type: token
+  example: "It took place between the second and third weeks of June"
+  action: mkDateRangeMentionBetweenWeeks
+  pattern: |
+    /(?i)between/ /(?i)the/? (?<week1> /(?i)(first|1st|second|2nd)/ /(?i)week/?) /(?i)(and|to)/ (?<week2> /(?i)(second|2nd|third|3rd|fourth|4th|last)/ /(?i)weeks?/) /(?i)of/ @month:PossibleMonth 
+
 - name: date-range-6
   priority: ${rulepriority}
   label: DateRange
@@ -101,7 +110,7 @@
   example: "First two weeks of May"
   action: mkDateRangeMentionWithWeek
   pattern: |
-    (?<week> /(?i)(first|second|last)/ /(?i)two/ /(?i)weeks/) /(?i)of/ @month:PossibleMonth
+    (?<week> /(?i)(first|second|last)/ /(?i)(two|three)/ /(?i)weeks/) /(?i)of/ @month:PossibleMonth
 
 - name: date-unbound-range-1
   priority: ${rulepriority}

main/src/main/scala/org/clulab/numeric/WeekNormalizer.scala

@@ -24,12 +24,12 @@ class WeekNormalizer(weekPath: String) {
 object WeekNormalizer {
 
   def readNormsFromResource(path: String): Map[String, WeekRange] = {
-    val customResourcePath = new File(NumericEntityRecognizer.resourceDir, path)
+    val customFile = new File(NumericEntityRecognizer.resourceDir, path)
+    val source =
+        if (customFile.exists) Sourcer.sourceFromFile(customFile)
+        else Sourcer.sourceFromResource(path)
 
-    if (customResourcePath.exists)
-      Using.resource(Sourcer.sourceFromFile(customResourcePath))(readNormsFromSource)
-    else
-      Using.resource(Sourcer.sourceFromResource(path))(readNormsFromSource)
+    Using.resource(source)(readNormsFromSource)
   }
 
   def readNormsFromSource(source: Source): Map[String, WeekRange] = {
@@ -38,14 +38,18 @@ object WeekNormalizer {
     CommentedStandardKbSource.read(source) { (week, normOpt, unitClassOpt) =>
       assert(normOpt.isDefined) // We're insisting on this.
 
+      val weeks = week.split('|').map(_.trim).filter(_.nonEmpty)
       val norm = normOpt.get.split("--").map(_.trim)
       val (start, end) = norm match {
         case Array(start, end) => (start, end)
         case _ => throw new RuntimeException(s"ERROR: incorrect date range in week file")
       }
       val startDay = getDay(start)
       val endDay = getDay(end)
-      norms += week -> WeekRange(startDay, endDay)
+      val weekRange = WeekRange(startDay, endDay)
+      val entries = weeks.map(_ -> weekRange)
+
+      norms ++= entries
     }
     norms.toMap
   }

main/src/main/scala/org/clulab/numeric/actions/NumericActions.scala

@@ -89,6 +89,11 @@ class NumericActions(seasonNormalizer: SeasonNormalizer, unitNormalizer: UnitNor
     convert(mentions, toDateRangeMentionWithMonth, "toDateRangeMentionWithMonth")
   }
 
+  /** Constructs a DateRangeMention from a token pattern */
+  def mkDateRangeMentionBetweenWeeks(mentions: Seq[Mention], state: State): Seq[Mention] = {
+    convert(mentions, toDateRangeMentionBetweenWeeks(weekNormalizer), "toDateRangeMentionBetweenWeeks")
+  }
+
   /** Constructs a DateRangeMention from a token pattern */
   def mkDateRangeMentionWithSinceRef(mentions: Seq[Mention], state: State): Seq[Mention] = {
     convert(mentions, toDateRangeMentionWithSinceRef, "toDateRangeMentionWithSinceRef")

main/src/main/scala/org/clulab/numeric/mentions/package.scala

@@ -212,6 +212,29 @@ package object mentions {
       throw new RuntimeException(s"ERROR: cannot convert mention of type [${m.getClass.toString}] to DateRangeMention!")
   }
 
+  def toDateRangeMentionBetweenWeeks(weekNormalizer: WeekNormalizer)(mention: Mention): DateRangeMention =  {
+
+    def throwRuntimeException(week: String): WeekRange = {
+      throw new RuntimeException(s"ERROR: could not find argument $week in mention [${mention.raw.mkString(" ")}]!")
+    }
+
+    mention match {
+      case m: DateRangeMention => m
+      case m: RelationMention =>
+        val w1Norm = getWeekRange(weekNormalizer)("week1", m).getOrElse(throwRuntimeException("week1"))
+        val w2Norm = getWeekRange(weekNormalizer)("week2", m).getOrElse(throwRuntimeException("week2"))
+        val monthOpt = getArgWords("month", m)
+
+        DateRangeMention(
+          m,
+          TempEvalFormatter.mkDate(w1Norm.startDay, monthOpt, None),
+          TempEvalFormatter.mkDate(w2Norm.endDay, monthOpt, None)
+        )
+      case m =>
+        throw new RuntimeException(s"ERROR: cannot convert mention of type [${m.getClass.toString}] to DateRangeMention!")
+    }
+  }
+
   def toDateRangeMentionWithMonth(mention: Mention): DateRangeMention =  mention match {
     case m: DateRangeMention => m
 
@@ -917,10 +940,17 @@ package object mentions {
   private def getWeekRange(weekNormalizer: WeekNormalizer)(argName: String, m:Mention): Option[WeekRange] = {
     val wordsOpt = getArgWords(argName, m)
 
-    if (wordsOpt.isEmpty) None
-    else if (wordsOpt.get.mkString(" ").toLowerCase().equals("last week")) {getLastWeekRange(m)}
-    else if (wordsOpt.get.mkString(" ").toLowerCase().equals("last two weeks")) {getLastTwoWeeksRange(m)}
-    else weekNormalizer.norm(wordsOpt.get)
+    wordsOpt.flatMap { words =>
+      val wordSeq = words.mkString(" ").toLowerCase()
+      //println(s"wordSeq = $wordSeq")
+
+      wordSeq match {
+        case "last week" => getLastWeekRange(m)
+        case "last two weeks" => getLastTwoWeeksRange(m)
+        case "last three weeks" => getLastThreeWeeksRange(m)
+        case _ => weekNormalizer.norm(words)
+      }
+    }
   }
 
   private def getLastWeekRange(m:Mention): Option[WeekRange] = {
@@ -941,6 +971,15 @@ package object mentions {
     Some(WeekRange(startDay = Some(Seq((lastDay - 13).toString)), endDay = Some(Seq(lastDay.toString))))
   }
 
+  private def getLastThreeWeeksRange(m:Mention): Option[WeekRange] = {
+    val month = getArgWords("month", m)
+    val modifiedMonth = TempEvalFormatter.convertLiteralMonth(month.get.mkString(""))
+    val monthObj = Month.of(modifiedMonth)
+    val lastDay = monthObj.length(false)
+
+    Some(WeekRange(startDay = Some(Seq((lastDay - 20).toString)), endDay = Some(Seq(lastDay.toString))))
+  }
+
   private def getHoliday(holiday: Seq[String], year: Option[Seq[String]]): (Option[Seq[String]], Option[Seq[String]]) = {
     val dayMonthOpt = HolidayNormalizer.norm(holiday, year)
     dayMonthOpt match {

main/src/test/scala/org/clulab/numeric/TestNumericEntityRecognition.scala

@@ -422,6 +422,14 @@ class TestNumericEntityRecognition extends Test {
     ensure(sentence = "We applied it in Fall in 21", Interval(4, 7), goldEntity= "DATE-RANGE", goldNorm = "XX21-09-22 -- XX21-12-21")
     ensure(sentence = "We applied it in fall of 2021", Interval(4, 7), goldEntity= "DATE-RANGE", goldNorm = "2021-09-22 -- 2021-12-21")
   }
+
+  it should "recognize between-week date ranges" in {
+    ensure("It took place between the second and third weeks of June",
+      Interval(3, 11), "DATE-RANGE", "XXXX-06-08 -- XXXX-06-21")
+
+    ensure("It took place between the first and 4th weeks of May",
+      Interval(3, 11), "DATE-RANGE", "XXXX-05-01 -- XXXX-05-28")
+  }
 
   it should "recognize measurement units" in {
     ensure("It was 12 ha", Interval(2, 4), "MEASUREMENT-AREA", "12.0 ha")