From 4006fdafcc16209f4cd240af932e8f066c884f6e Mon Sep 17 00:00:00 2001
From: adamd1008 <a-dodd@outlook.com>
Date: Thu, 25 Jan 2024 17:47:51 +0000
Subject: [PATCH] Added switch to include Chi-squared p-value in terse output

---
 src/ent.c    | 35 +++++++++++++++++++++++++----------
 src/ent.html | 23 +++++++++++++++++++++--
 2 files changed, 46 insertions(+), 12 deletions(-)

diff --git a/src/ent.c b/src/ent.c
index bf981bc..47e6971 100644
--- a/src/ent.c
+++ b/src/ent.c
@@ -59,6 +59,7 @@ static void help(void)
         printf("\n                   -c   Print occurrence counts");
         printf("\n                   -f   Fold upper to lower case letters");
         printf("\n                   -t   Terse output in CSV format");
+        printf("\n                   -p   Include Chi-square p-value in terse output (as decimal)");
         printf("\n                   -u   Print this message\n");
         printf("\nVersion " VERSION);
         printf("\nBy John Walker");
@@ -107,9 +108,10 @@ int main(int argc, char *argv[])
         int counts = FALSE,           /* Print character counts */
             fold = FALSE,             /* Fold upper to lower */
             binary = FALSE,           /* Treat input as a bitstream */
-            terse = FALSE;            /* Terse (CSV format) output */
+            terse = FALSE,            /* Terse (CSV format) output */
+            csp = FALSE;              /* Terse includes Chi^2 p-value */
 
-        while ((opt = getopt(argc, argv, "bcftuv?BCFTUV")) != -1) {
+        while ((opt = getopt(argc, argv, "bcfptuv?BCFPTUV")) != -1) {
             switch (toISOlower(opt)) {
                  case 'b':
                     binary = TRUE;
@@ -123,6 +125,10 @@ int main(int argc, char *argv[])
                     fold = TRUE;
                     break;
 
+                 case 'p':
+                    csp = TRUE;
+                    break;
+
                  case 't':
                     terse = TRUE;
                     break;
@@ -200,22 +206,31 @@ int main(int argc, char *argv[])
         }
         fclose(fp);
 
-        /* Complete calculation and return sequence metrics */
+        /* Complete calculation */
 
         rt_end(&ent, &chisq, &mean, &montepi, &scc);
 
-        if (terse) {
-           printf("0,File-%ss,Entropy,Chi-square,Mean,Monte-Carlo-Pi,Serial-Correlation\n",
-              binary ? "bit" : "byte");
-           printf("1,%ld,%f,%f,%f,%f,%f\n",
-              totalc, ent, chisq, mean, montepi, scc);
-        }
-
         /* Calculate probability of observed distribution occurring from
            the results of the Chi-Square test */
 
         chip = pochisq(chisq, (binary ? 1 : 255));
 
+        /* Return sequence metrics */
+
+        if (terse) {
+            if (csp) {
+                printf("0,File-%ss,Entropy,Chi-square,Chi-square-p-val,Mean,Monte-Carlo-Pi,Serial-Correlation\n",
+                   binary ? "bit" : "byte");
+                printf("1,%ld,%f,%f,%f,%f,%f,%f\n",
+                   totalc, ent, chisq, chip, mean, montepi, scc);
+            } else {
+                printf("0,File-%ss,Entropy,Chi-square,Mean,Monte-Carlo-Pi,Serial-Correlation\n",
+                   binary ? "bit" : "byte");
+                printf("1,%ld,%f,%f,%f,%f,%f\n",
+                   totalc, ent, chisq, mean, montepi, scc);
+            }
+        }
+
         /* Print bin counts if requested */
 
         if (counts) {
diff --git a/src/ent.html b/src/ent.html
index 77e2e59..f153758 100644
--- a/src/ent.html
+++ b/src/ent.html
@@ -127,7 +127,7 @@ <h3>NAME</h3>
 
 <h3>SYNOPSIS</h3>
 
-     <b>ent</b> [ <b>-b -c -f -t -u</b> ] [ <i>infile</i> ]
+     <b>ent</b> [ <b>-b -c -f -p -t -u</b> ] [ <i>infile</i> ]
 
 <h3>DESCRIPTION</h3>
 
@@ -304,6 +304,12 @@ <h3>OPTIONS</h3>
                <a href="#Terse">Terse Mode Output Format</a>
                below for additional details.</dd>
 
+<dt><b>-p</b></dt>  <dd>Used in conjunction with <b>-t</b> to
+               include the Chi-squared p-value in the terse
+               output (as decimal).  See
+               <a href="#Terse">Terse Mode Output Format</a>
+               below for additional details.</dd>
+
 <dt><b>-u</b></dt>  <dd>Print how-to-call information.</dd>
 </dl>
 
@@ -340,7 +346,20 @@ <h3><a name="Terse" class="i">TERSE MODE OUTPUT FORMAT</a></h3>
 column title record.  If the <b>-b</b> option is specified, the second
 field of the type 0 record will be &ldquo;<tt>File-bits</tt>&rdquo;, and
 the <em>file_length</em> field in type 1 record will be given
-in bits instead of bytes.  If the <b>-c</b> option is specified,
+in bits instead of bytes.
+</p>
+
+<p>
+Specifying <b>-p</b> in conjunction with <b>-t</b> includes the Chi-squared p-value in the CSV output. Note that it is provided as decimal, not as a percentage. When specified, the output becomes:
+</p>
+
+<pre>
+0,File-bytes,Entropy,Chi-square,Chi-square-p-val,Mean,Monte-Carlo-Pi,Serial-Correlation
+1,<em>file_length</em>,<em>entropy</em>,<em>chi_square</em>,<em>chi_square_p_val</em>,<em>mean</em>,<em>Pi_value</em>,<em>correlation</em>
+</pre>
+
+<p>
+If the <b>-c</b> option is specified,
 additional records are appended to the terse mode output which
 contain the character counts:
 </p>