Implement --set-page-labels and supporting API (fixes #939)

3 files changed, 112 insertions, 8 deletions

diff --git a/libqpdf/QPDFJob.cc b/libqpdf/QPDFJob.cc
index b0910cbd..2e0abb43 100644
--- a/libqpdf/QPDFJob.cc
+++ b/libqpdf/QPDFJob.cc
@@ -2172,6 +2172,37 @@ QPDFJob::handleTransformations(QPDF& pdf)
     if (m->remove_page_labels) {
         pdf.getRoot().removeKey("/PageLabels");
     }
+    if (!m->page_label_specs.empty()) {
+        auto nums = QPDFObjectHandle::newArray();
+        auto n_pages = QIntC::to_int(dh.getAllPages().size());
+        int last_page_seen{0};
+        for (auto& spec: m->page_label_specs) {
+            if (spec.first_page < 0) {
+                spec.first_page = n_pages + 1 + spec.first_page;
+            }
+            if (last_page_seen == 0) {
+                if (spec.first_page != 1) {
+                    throw std::runtime_error(
+                        "the first page label specification must start with page 1");
+                }
+            } else if (spec.first_page <= last_page_seen) {
+                throw std::runtime_error(
+                    "page label specifications must be in order by first page");
+            }
+            if (spec.first_page > n_pages) {
+                throw std::runtime_error(
+                    "page label spec: page " + std::to_string(spec.first_page) +
+                    " is more than the total number of pages (" + std::to_string(n_pages) + ")");
+            }
+            last_page_seen = spec.first_page;
+            nums.appendItem(QPDFObjectHandle::newInteger(spec.first_page - 1));
+            nums.appendItem(QPDFPageLabelDocumentHelper::pageLabelDict(
+                spec.label_type, spec.start_num, spec.prefix));
+        }
+        auto page_labels = QPDFObjectHandle::newDictionary();
+        page_labels.replaceKey("/Nums", nums);
+        pdf.getRoot().replaceKey("/PageLabels", page_labels);
+    }
     if (!m->attachments_to_remove.empty()) {
         QPDFEmbeddedFileDocumentHelper efdh(pdf);
         for (auto const& key: m->attachments_to_remove) {
@@ -3019,10 +3050,9 @@ QPDFJob::writeOutfile(QPDF& pdf)
             try {
                 QUtil::remove_file(backup.c_str());
             } catch (QPDFSystemError& e) {
-                *m->log->getError()
-                    << m->message_prefix << ": unable to delete original file (" << e.what() << ");"
-                    << " original file left in " << backup
-                    << ", but the input was successfully replaced\n";
+                *m->log->getError() << m->message_prefix << ": unable to delete original file ("
+                                    << e.what() << ");" << " original file left in " << backup
+                                    << ", but the input was successfully replaced\n";
             }
         }
     }
diff --git a/libqpdf/QPDFJob_config.cc b/libqpdf/QPDFJob_config.cc
index 9651c3b9..e48d7e31 100644
--- a/libqpdf/QPDFJob_config.cc
+++ b/libqpdf/QPDFJob_config.cc
@@ -1,5 +1,7 @@
 #include <qpdf/QPDFJob.hh>
 
+#include <regex>
+
 #include <qpdf/QPDFLogger.hh>
 #include <qpdf/QTC.hh>
 #include <qpdf/QUtil.hh>
@@ -1062,11 +1064,50 @@ QPDFJob::Config::encrypt(
 QPDFJob::Config*
 QPDFJob::Config::setPageLabels(const std::vector<std::string>& specs)
 {
-    // XXX validate
-    for (auto const& xxx: specs) {
-        std::cout << "XXX config: spec: " << xxx << std::endl;
+    static std::regex page_label_re(R"(^(z|r?\d+):([DaArR])?(?:/(\d+)?(?:/(.+)?)?)?$)");
+    o.m->page_label_specs.clear();
+    for (auto const& spec: specs) {
+        std::smatch match;
+        if (!std::regex_match(spec, match, page_label_re)) {
+            usage("page label spec must be n:[D|a|A|r|R][/start[/prefix]]");
+        }
+        auto first_page_str = match[1].str();
+        int first_page;
+        if (first_page_str == "z") {
+            first_page = -1;
+        } else if (first_page_str.at(0) == 'r') {
+            first_page = -QUtil::string_to_int(first_page_str.substr(1).c_str());
+        } else {
+            first_page = QUtil::string_to_int(first_page_str.c_str());
+        }
+        auto label_type_ch = match[2].matched ? match[2].str().at(0) : '\0';
+        qpdf_page_label_e label_type;
+        switch (label_type_ch) {
+        case 'D':
+            label_type = pl_digits;
+            break;
+        case 'a':
+            label_type = pl_alpha_lower;
+            break;
+        case 'A':
+            label_type = pl_alpha_upper;
+            break;
+        case 'r':
+            label_type = pl_roman_lower;
+            break;
+        case 'R':
+            label_type = pl_roman_upper;
+            break;
+        default:
+            label_type = pl_none;
+        }
+
+        auto start_num = match[3].matched ? QUtil::string_to_int(match[3].str().c_str()) : 1;
+        auto prefix = match[4].matched ? match[4].str() : "";
+        // We can't check ordering until we know how many pages there are, so that is delayed until
+        // near the end.
+        o.m->page_label_specs.emplace_back(first_page, label_type, start_num, prefix);
     }
-    o.m->page_label_specs = specs;
     return this;
 }
 
diff --git a/libqpdf/QPDFPageLabelDocumentHelper.cc b/libqpdf/QPDFPageLabelDocumentHelper.cc
index d94c41fd..e291e9aa 100644
--- a/libqpdf/QPDFPageLabelDocumentHelper.cc
+++ b/libqpdf/QPDFPageLabelDocumentHelper.cc
@@ -99,3 +99,36 @@ QPDFPageLabelDocumentHelper::getLabelsForPageRange(
         }
     }
 }
+
+QPDFObjectHandle
+QPDFPageLabelDocumentHelper::pageLabelDict(
+    qpdf_page_label_e label_type, int start_num, std::string_view prefix)
+{
+    auto num = "<< /Type /PageLabel >>"_qpdf;
+    switch (label_type) {
+    case pl_none:
+        break;
+    case pl_digits:
+        num.replaceKey("/S", "/D"_qpdf);
+        break;
+    case pl_alpha_lower:
+        num.replaceKey("/S", "/a"_qpdf);
+        break;
+    case pl_alpha_upper:
+        num.replaceKey("/S", "/A"_qpdf);
+        break;
+    case pl_roman_lower:
+        num.replaceKey("/S", "/r"_qpdf);
+        break;
+    case pl_roman_upper:
+        num.replaceKey("/S", "/R"_qpdf);
+        break;
+    }
+    if (!prefix.empty()) {
+        num.replaceKey("/P", QPDFObjectHandle::newUnicodeString(std::string(prefix)));
+    }
+    if (start_num != 1) {
+        num.replaceKey("/St", QPDFObjectHandle::newInteger(start_num));
+    }
+    return num;
+}