#!/bin/sh
#
# Conjecturally Secure Pseudo-Random Document Generator
#
# Copyright (c) 2026 Doan Luu Duc Tai doan@luuduct.ai
# SPDX-License-Identifier: 0BSD OR Apache-2.0
#
# This script is dual-licensed under the Zero-Clause BSD License (0BSD)
# OR the Apache License, Version 2.0 (Apache-2.0), at your option.
# See the LICENSE file for the full text of both licenses.

OUTPUT_FILE="document.odt"

SCRIPT_DIR=$(dirname "$0")
WORDLIST="$SCRIPT_DIR/words.txt"

if [ ! -r "$WORDLIST" ]; then
  printf "Error: The required word list was not found or is not readable at:\n" >&2
  printf "       %s\n" "$WORDLIST" >&2
  printf "Please ensure 'words.txt' is placed in the same folder as this script.\n" >&2
  exit 1
fi

if ! command -v zip >/dev/null 2>&1; then
  printf "Error: The 'zip' utility is required but was not found in PATH.\n" >&2
  exit 1
fi

TMP_DIR="./odt_tmp_$$"
mkdir -p "$TMP_DIR"

cleanup() {
  rm -rf "$TMP_DIR"
}
trap cleanup 0 INT TERM

mkdir -p "$TMP_DIR/META-INF"

printf "application/vnd.oasis.opendocument.text" >"$TMP_DIR/mimetype"

cat <<'EOF' >"$TMP_DIR/META-INF/manifest.xml"
<?xml version="1.0" encoding="UTF-8"?>
<manifest:manifest xmlns:manifest="urn:oasis:names:tc:opendocument:xmlns:manifest:1.0" manifest:version="1.2">
  <manifest:file-entry manifest:full-path="/" manifest:version="1.2" manifest:media-type="application/vnd.oasis.opendocument.text"/>
  <manifest:file-entry manifest:full-path="content.xml" manifest:media-type="text/xml"/>
  <manifest:file-entry manifest:full-path="styles.xml" manifest:media-type="text/xml"/>
  <manifest:file-entry manifest:full-path="meta.xml" manifest:media-type="text/xml"/>
  <manifest:file-entry manifest:full-path="settings.xml" manifest:media-type="text/xml"/>
</manifest:manifest>
EOF

cat <<'EOF' >"$TMP_DIR/styles.xml"
<?xml version="1.0" encoding="UTF-8"?>
<office:document-styles xmlns:office="urn:oasis:names:tc:opendocument:xmlns:office:1.0" xmlns:style="urn:oasis:names:tc:opendocument:xmlns:style:1.0" office:version="1.2">
  <office:styles>
    <style:default-style style:family="paragraph"/>
  </office:styles>
  <office:automatic-styles/>
  <office:master-styles>
    <style:master-page style:name="Standard"/>
  </office:master-styles>
</office:document-styles>
EOF

cat <<'EOF' >"$TMP_DIR/meta.xml"
<?xml version="1.0" encoding="UTF-8"?>
<office:document-meta xmlns:office="urn:oasis:names:tc:opendocument:xmlns:office:1.0" xmlns:meta="urn:oasis:names:tc:opendocument:xmlns:meta:1.0" office:version="1.2">
  <office:meta>
    <meta:generator>POSIX Shell ODT Generator</meta:generator>
  </office:meta>
</office:document-meta>
EOF

cat <<'EOF' >"$TMP_DIR/settings.xml"
<?xml version="1.0" encoding="UTF-8"?>
<office:document-settings xmlns:office="urn:oasis:names:tc:opendocument:xmlns:office:1.0" office:version="1.2">
  <office:settings/>
</office:document-settings>
EOF

SEED=$( (
  date
  times 2>/dev/null
  ls -l /tmp 2>/dev/null
  env 2>/dev/null
) | cksum | awk '{print $1}')

case "$SEED" in
"" | *[!0-9]*) SEED=123456 ;;
esac

awk -v seed="$SEED" -v stats_file="$TMP_DIR/stats" '
BEGIN {
    srand(seed);
    word_count = 0;

    pages = int(50 + rand() * 31);
    
    min_words = pages * 200;
    if (min_words < 10000) {
        min_words = 10000;
    }
    total_words = min_words + int(rand() * 5001);
}

/^[[:alpha:]]+$/ {
    if (word_count < 50000) {
        words[word_count] = $0;
        word_count++;
    }
}

END {
    if (word_count == 0) {
        print "ERROR=\"No usable words found in the system wordlist.\"" > stats_file;
        exit 1;
    }

    print "PAGES=" pages > stats_file;
    print "WORDS=" total_words > stats_file;

    print "<?xml version=\"1.0\" encoding=\"UTF-8\"?>";
    print "<office:document-content xmlns:office=\"urn:oasis:names:tc:opendocument:xmlns:office:1.0\" xmlns:style=\"urn:oasis:names:tc:opendocument:xmlns:style:1.0\" xmlns:text=\"urn:oasis:names:tc:opendocument:xmlns:text:1.0\" xmlns:table=\"urn:oasis:names:tc:opendocument:xmlns:table:1.0\" xmlns:draw=\"urn:oasis:names:tc:opendocument:xmlns:drawing:1.0\" xmlns:fo=\"urn:oasis:names:tc:opendocument:xmlns:xsl-fo-compatible:1.0\" xmlns:xlink=\"http://www.w3.org/1999/xlink\" xmlns:meta=\"urn:oasis:names:tc:opendocument:xmlns:meta:1.0\" office:version=\"1.2\">";
    print "  <office:automatic-styles>";
    print "    <style:style style:name=\"PB\" style:family=\"paragraph\">";
    print "      <style:paragraph-properties fo:break-before=\"page\"/>";
    print "    </style:style>";
    print "  </office:automatic-styles>";
    print "  <office:body>";
    print "    <office:text>";

    w_per_page = int(total_words / pages);
    words_left = total_words;

    for (p = 1; p <= pages; p++) {
        if (p == pages) {
            p_words = words_left;
        } else {
            variation = int(w_per_page * 0.2);
            if (variation < 5) {
                variation = 5;
            }
            p_words = w_per_page + int(rand() * (variation * 2 + 1)) - variation;
            if (p_words > words_left) {
                p_words = words_left;
            }
            if (p_words < 10) {
                p_words = 10;
            }
        }
        words_left -= p_words;

	if (p > 1) {
	   is_first_p = 1;
	} else {
	   is_first_p = 0;
	}
        while (p_words > 0) {
            p_len = int(25 + rand() * 36);
            if (p_len > p_words) {
                p_len = p_words;
            }
            p_words -= p_len;

            if (is_first_p) {
                printf "      <text:p text:style-name=\"PB\">";
                is_first_p = 0;
            } else {
                printf "      <text:p>";
            }

            for (w = 0; w < p_len; w++) {
                rnd_idx = int(rand() * word_count);
                word = words[rnd_idx];
                
                if (w == 0) {
                    word = toupper(substr(word, 1, 1)) substr(word, 2);
                } else {
                    word = tolower(word);
                }
                
                printf "%s", word;
                if (w == p_len - 1) {
                    printf(".");
                } else {
                    printf(" ");
                }
            }
            print "</text:p>";
        }
    }

    print "    </office:text>";
    print "  </office:body>";
    print "</office:document-content>";
}
' "$WORDLIST" >"$TMP_DIR/content.xml"

if [ -f "$TMP_DIR/stats" ]; then
  . "$TMP_DIR/stats"
fi

if [ -n "$ERROR" ]; then
  printf "Error: %s\n" "$ERROR" >&2
  exit 1
fi

case "$OUTPUT_FILE" in
/*) ABS_OUTPUT="$OUTPUT_FILE" ;;
*) ABS_OUTPUT="$(pwd)/$OUTPUT_FILE" ;;
esac

rm -f "$ABS_OUTPUT"

(
  cd "$TMP_DIR" || exit 1
  zip -X -r -n mimetype "$ABS_OUTPUT" mimetype META-INF content.xml styles.xml meta.xml settings.xml >/dev/null
)

if [ $? -eq 0 ]; then
  printf "Document successfully created: %s\n" "$OUTPUT_FILE"
  printf "Generated Details:\n"
  printf "  - Pages: %s\n" "$PAGES"
  printf "  - Words: %s\n" "$WORDS"
else
  printf "Error: Failed to package ODT using zip.\n" >&2
  exit 1
fi