From 4d9cbde822f60b92d86a1319f5b2a9971c5af5d0 Mon Sep 17 00:00:00 2001
From: Dan Lowe <dan@tangledhelix.com>
Date: Wed, 31 Dec 2025 00:40:22 -0500
Subject: [PATCH 1/3] find ranges of page numbers

ports a feature from PPtools: find page numbers in various formats and
display them (roman first, arabic next). understands different formats
like Page_1, page_1, page1 (in id attribute) and attempts to parse out
span class=pagenum formats like p. 1, [Pg 1] and so forth.
---
 pphtml.py        | 114 +++++++++++++++++++++++++++++++++++++++++++++++
 requirements.txt |   1 +
 2 files changed, 115 insertions(+)

diff --git a/pphtml.py b/pphtml.py
index 5685048..f449f00 100644
--- a/pphtml.py
+++ b/pphtml.py
@@ -11,6 +11,8 @@
 import sys
 import os
 import argparse
+import itertools
+import roman
 from time import strftime
 from html.parser import HTMLParser
 import regex as re  # for unicode support  (pip install regex)
@@ -73,6 +75,8 @@ class initialization
         self.udefcss = {}  # user defined CSS
         self.usedcss = {}  # CSS used by user
         self.errormessage = ""  # for unwrap failure
+        self.ranges_arabic = []
+        self.ranges_roman = []
 
     def crash(self):
         self.saveReport()
@@ -462,6 +466,115 @@ def cleanExt(self):
             r.append("[pass] external links check")
         self.apl(r)
 
+    def documentInfo(self):
+        """
+        Section to contain general document information
+        """
+        self.ap("")
+        t = "document info"
+        self.ap("----- {} ".format(t) + "-" * (73 - len(t)))
+        self.findPageRanges()
+
+
+    def findPageRanges(self):
+        """
+        Find ranges of page locations for later reporting
+        """
+        r = []
+        pages_arabic = []
+        pages_roman = []
+
+        # Look for <a>, <div>, <span> with 'id' attribute; \3 is the match
+        pat1 = re.compile(r"""<(a|div|span)\s+[^>]*\bid=["'](page|pg)_?([\divxlcdm]+)["']""",
+                          re.IGNORECASE)
+        # Alternately: look for span class=pagenum; \1 is the match
+        pat2 = re.compile(r"""<span\s+[^>]*\bclass=["']pagenum['"].*>([^<]+)</span""",
+                          re.IGNORECASE)
+
+        for line in self.wb:
+            m = pat1.search(line)
+            if m:
+                if m.group(3).isnumeric():
+                    pages_arabic.append(int(m.group(3)))
+                else:
+                    try:
+                        n = roman.fromRoman(m.group(3))
+                        pages_roman.append(m.group(3))
+                    except roman.InvalidRomanNumeralError:
+                        # we tried...
+                        continue
+
+                # don't check the same line again if it already matched
+                continue
+
+            m = pat2.search(line)
+            if m:
+                text = m.group(1)
+                text = text.replace("Page_", "")
+                text = text.replace("page_", "")
+                text = text.replace("page", "")
+                text = text.replace("[", "")
+                text = text.replace("]", "")
+                text = text.replace("p.", "")
+                text = text.replace("P.", "")
+                text = text.replace("Pg.", "")
+                text = text.replace("Pg", "")
+                text = text.strip()
+
+                if m.group(1).isnumeric():
+                    pages_arabic.append(int(m.group(1)))
+                else:
+                    try:
+                        n = roman.fromRoman(m.group(3))
+                        pages_roman.append(m.group(3))
+                    except roman.InvalidRomanNumeralError:
+                        # we tried...
+                        continue
+
+        # Create ranges
+        # Uses Python magic to go from [1,2,5,6,7] to [[1,2],[5,7]]
+
+        # Arabic
+        R = (list(x) for _, x in itertools.groupby(pages_arabic, lambda x, c=itertools.count(): next(c)-x))
+        self.ranges_arabic = [[r[0], r[-1]] for r in R]
+        last = -1
+        for myrange in self.ranges_arabic:
+            page_l, page_h = myrange
+
+            if page_h == last:
+                myrange.append("Page (or set of pages) is duplicated")
+            elif page_h < last:
+                myrange.append("Page (or set of pages) is out of sequence")
+            else:
+                myrange.append(None)
+
+            last = page_h
+
+        # Roman
+        R = (list(x) for _, x in itertools.groupby(pages_roman, lambda x, c=itertools.count(): next(c)-roman.fromRoman(x.upper())))
+        self.ranges_roman = [[r[0], r[-1]] for r in R]
+        last = -1
+        for myrange in self.ranges_roman:
+            page_l, page_h = myrange
+
+            if roman.fromRoman(page_h.upper()) == last:
+                myrange.append("Page (or set of pages) is duplicated")
+            elif roman.fromRoman(page_h.upper()) < last:
+                myrange.append("Page (or set of pages) is out of sequence")
+            else:
+                myrange.append(None)
+
+            last = roman.fromRoman(page_h.upper())
+
+        r.append("[info] page numbers ( roman): " +
+            ", ".join([f"{r[0]}–{r[1]}" for r in self.ranges_roman])
+        )
+        r.append("[info] page numbers (arabic): " +
+            ", ".join([f"{r[0]}–{r[1]}" for r in self.ranges_arabic])
+        )
+
+        self.apl(r)
+
     def linkToCover(self):
         """
         either: provide a link in the document head, or
@@ -1255,6 +1368,7 @@ def run(self):
         """
 
         self.loadFile()
+        self.documentInfo()
         self.imageTests()
         self.linkTests()
         self.ppvTests()
diff --git a/requirements.txt b/requirements.txt
index bb4f569..aca530d 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,2 +1,3 @@
 Pillow>=7.1.0
 regex>=2019.4.12
+roman>=5.2

From 88f15b8abfc21ee46b5e1f0ab3b568e8fa69592e Mon Sep 17 00:00:00 2001
From: Dan Lowe <dan@tangledhelix.com>
Date: Wed, 31 Dec 2025 15:17:54 -0500
Subject: [PATCH 2/3] follow import sorting/grouping convention

---
 pphtml.py | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/pphtml.py b/pphtml.py
index f449f00..fe1f0e5 100644
--- a/pphtml.py
+++ b/pphtml.py
@@ -8,15 +8,16 @@
 # pylint: disable=C0103, R0912, R0915
 # pylint: disable=too-many-instance-attributes, too-many-locals, no-self-use
 
-import sys
-import os
 import argparse
 import itertools
-import roman
-from time import strftime
+import os
+import sys
 from html.parser import HTMLParser
-import regex as re  # for unicode support  (pip install regex)
+from time import strftime
+
 from PIL import Image  # from pip install pillow
+import regex as re  # for unicode support  (pip install regex)
+import roman  # for pphtml
 
 
 class MyHTMLParser(HTMLParser):

From 3eb45f7f510e0b094a87e63236a012be7e8933de Mon Sep 17 00:00:00 2001
From: Dan Lowe <dan@tangledhelix.com>
Date: Thu, 1 Jan 2026 02:40:53 -0500
Subject: [PATCH 3/3] =?UTF-8?q?Show=20'3',=20not=20'3=E2=80=933'=20when=20?=
 =?UTF-8?q?page=20range=20is=201=20page=20long?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 pphtml.py | 23 +++++++++++++++++------
 1 file changed, 17 insertions(+), 6 deletions(-)

diff --git a/pphtml.py b/pphtml.py
index fe1f0e5..b18359f 100644
--- a/pphtml.py
+++ b/pphtml.py
@@ -567,12 +567,23 @@ def findPageRanges(self):
 
             last = roman.fromRoman(page_h.upper())
 
-        r.append("[info] page numbers ( roman): " +
-            ", ".join([f"{r[0]}–{r[1]}" for r in self.ranges_roman])
-        )
-        r.append("[info] page numbers (arabic): " +
-            ", ".join([f"{r[0]}–{r[1]}" for r in self.ranges_arabic])
-        )
+        # render found page ranges list (roman)
+        _rbuf = []
+        for _r in self.ranges_roman:
+            if _r[0] == _r[1]:
+                _rbuf.append(_r[0])
+            else:
+                _rbuf.append(f"{_r[0]}–{_r[1]}")
+        r.append(f"[info] page numbers ( roman): {', '.join(_rbuf)}")
+
+        # render found page ranges list (arabic)
+        _abuf = []
+        for _a in self.ranges_arabic:
+            if _a[0] == _a[1]:
+                _abuf.append(str(_a[0]))
+            else:
+                _abuf.append(f"{_a[0]}–{_a[1]}")
+        r.append(f"[info] page numbers (arabic): {', '.join(_abuf)}")
 
         self.apl(r)