June 2018 Update

Task/Text-processing-2/00DESCRIPTION

@@ -4,7 +4,9 @@ The fields (from the left) are:
   DATESTAMP [ VALUEn FLAGn ] * 24
 i.e. a datestamp followed by twenty-four repetitions of a floating-point instrument value and that instrument's associated integer flag. Flag values are >= 1 if the instrument is working and < 1 if there is some problem with it, in which case that instrument's value should be ignored.
 
-A sample from the full data file [http://rosettacode.org/resources/readings.zip readings.txt], which is also used in the [[Data Munging]] task, follows:
+A sample from the full data file [http://rosettacode.org/resources/readings.zip readings.txt], which is also used in the [[Text processing/1]] task, follows:
+
+Data is no longer available at that link. Zipped mirror available [https://github.com/thundergnat/rc/blob/master/resouces/readings.zip here]
 <pre>
 1991-03-30	10.000	1	10.000	1	10.000	1	10.000	1	10.000	1	10.000	1	10.000	1	10.000	1	10.000	1	10.000	1	10.000	1	10.000	1	10.000	1	10.000	1	10.000	1	10.000	1	10.000	1	10.000	1	10.000	1	10.000	1	10.000	1	10.000	1	10.000	1	10.000	1
 1991-03-31	10.000	1	10.000	1	10.000	1	10.000	1	10.000	1	10.000	1	10.000	1	20.000	1	20.000	1	20.000	1	35.000	1	50.000	1	60.000	1	40.000	1	30.000	1	30.000	1	30.000	1	25.000	1	20.000	1	20.000	1	20.000	1	20.000	1	20.000	1	35.000	1

Task/Text-processing-2/Aime/text-processing-2.aime

@@ -4,21 +4,21 @@ check_format(list l)
     integer i;
     text s;
 
-    if (l_length(l) != 49) {
+    if (~l != 49) {
         error("wrong number of fields");
     }
 
-    s = lf_q_text(l);
-    if (length(s) != 10 || s[4] != '-' || s[7] != '-') {
+    s = l[0];
+    if (~s != 10 || s[4] != '-' || s[7] != '-') {
         error("bad date format");
     }
-    atoi(delete(delete(s, 7), 4));
+    l[0] = atoi(delete(delete(s, 7), 4));
 
     i = 1;
     while (i < 49) {
-        l_r_real(l, i, atof(l_q_text(l, i)));
+        l[i] = atof(l[i]);
         i += 1;
-        l_r_integer(l, i, atoi(l_q_text(l, i)));
+        l[i] = atoi(l[i]);
         i += 1;
     }
 }
@@ -26,39 +26,36 @@ check_format(list l)
 integer
 main(void)
 {
-    integer goods;
+    integer goods, i, v;
     file f;
     list l;
-    record r;
+    index x;
 
     goods = 0;
 
-    f_affix(f, "readings.txt");
+    f.affix("readings.txt");
 
-    while (f_list(f, l, 0) != -1) {
+    while (f.list(l, 0) != -1) {
         if (!trap(check_format, l)) {
-            if (r_key(r, l_head(l))) {
-                v_form("duplicate ~ line\n", l_head(l));
-            } else {
-                integer i;
+            if (x.key(v = lf_pick(l))) {
+                v_form("duplicate ~ line\n", v);
+            }
 
-                r_put(r, l_head(l), 0);
-                i = 2;
-                while (i < 49) {
-                    if (l_q_integer(l, i) != 1) {
-                        break;
-                    }
-                    i += 2;
-                }
-                if (49 < i) {
-                    goods += 1;
+            x[v] = 0;
+            i = 1;
+            while (i < 48) {
+                if (l[i] < 1) {
+                    break;
                 }
+                i += 2;
+            }
+            if (48 < i) {
+                goods += 1;
             }
         }
     }
 
-    o_integer(goods);
-    o_text(" good unique lines\n");
+    o_(goods, " good lines\n");
 
     return 0;
 }

Task/Text-processing-2/Julia/text-processing-2.julia

@@ -0,0 +1,5 @@
+dupdate = df[nonunique(df[:,[:Date]]),:][:Date]
+println("The following rows have duplicate DATESTAMP:")
+println(df[df[:Date] .== dupdate,:])
+println("All values good in these rows:")
+println(df[df[:ValidValues] .== 24,:])

Task/Text-processing-2/Kotlin/text-processing-2.kotlin

@@ -0,0 +1,42 @@
+// version 1.2.31
+
+import java.io.File
+
+fun main(args: Array<String>) {
+    val rx = Regex("""\s+""")
+    val file = File("readings.txt")
+    var count = 0
+    var invalid = 0
+    var allGood = 0
+    var map = mutableMapOf<String, Int>()
+    file.forEachLine { line ->
+        count++
+        val fields = line.split(rx)
+        val date = fields[0]
+        if (fields.size == 49) {
+            if (map.containsKey(date))
+                map[date] = map[date]!! + 1
+            else
+                map.put(date, 1)
+            var good = 0
+            for (i in 2 until fields.size step 2) {
+                if (fields[i].toInt() >= 1) {
+                    good++
+                }
+            }
+            if (good == 24) allGood++
+        }
+        else invalid++
+    }
+
+    println("File = ${file.name}")
+    println("\nDuplicated dates:")
+    for ((k,v) in map) {
+        if (v > 1) println("  $k ($v times)")
+    }
+    println("\nTotal number of records   : $count")
+    var percent = invalid.toDouble() / count * 100.0
+    println("Number of invalid records : $invalid (${"%5.2f".format(percent)}%)")
+    percent = allGood.toDouble() / count * 100.0
+    println("Number which are all good : $allGood (${"%5.2f".format(percent)}%)")
+}

Task/Text-processing-2/Perl-6/text-processing-2.pl6

@@ -0,0 +1,19 @@
+my $good-records;
+my $line;
+my %dates;
+
+for lines() {
+    $line++;
+    / ^
+    (\d ** 4 '-' \d\d '-' \d\d)
+    [ \h+ \d+'.'\d+ \h+ ('-'?\d+) ] ** 24
+    $ /
+        or note "Bad format at line $line" and next;
+    %dates.push: $0 => $line;
+    $good-records++ if $1.all >= 1;
+}
+
+say "$good-records good records out of $line total";
+
+say 'Repeated timestamps (with line numbers):';
+.say for sort %dates.pairs.grep: *.value.elems > 1;