feat: propose business-sender candidates, always commented out

3 files changed, 211 insertions, 0 deletions

diff --git a/src/businesssenders.cpp b/src/businesssenders.cpp
index 13a9374..06f4d43 100644
--- a/src/businesssenders.cpp
+++ b/src/businesssenders.cpp
@@ -20,6 +20,7 @@
 
 #include <QDir>
 #include <QFile>
+#include <QFileInfo>
 #include <QStandardPaths>
 #include <QTextStream>
 
@@ -75,4 +76,84 @@ QString defaultPath()
         QStringLiteral("qtmaildir/business-senders"));
 }
 
+bool looksLikeBulk(const QString &address)
+{
+    static const QStringList kBulkLocalParts {
+        QStringLiteral("noreply"),     QStringLiteral("no-reply"),
+        QStringLiteral("donotreply"),  QStringLiteral("do-not-reply"),
+        QStringLiteral("info"),        QStringLiteral("support"),
+        QStringLiteral("billing"),     QStringLiteral("newsletter"),
+        QStringLiteral("notifications"), QStringLiteral("mailer-daemon"),
+    };
+    const int at = address.indexOf(QLatin1Char('@'));
+    if (at <= 0)
+        return false;
+    const QString local = address.left(at).toLower();
+    for (const QString &candidate : kBulkLocalParts) {
+        if (local == candidate || local.startsWith(candidate))
+            return true;
+    }
+    return false;
+}
+
+void appendCandidates(const QString &path, const QHash<QString, int> &counts)
+{
+    // Every address the file MENTIONS, active or rejected. Parsed separately
+    // from parse() above, which deliberately drops comments: here a comment is
+    // exactly what must be remembered.
+    QSet<QString> mentioned;
+    QFile existing(path);
+    if (existing.open(QIODevice::ReadOnly | QIODevice::Text)) {
+        const QStringList lines =
+            QString::fromUtf8(existing.readAll()).split(QLatin1Char('\n'));
+        for (const QString &raw : lines) {
+            QString line = raw.trimmed();
+            if (line.startsWith(QLatin1Char('#')))
+                line = line.mid(1).trimmed();
+            if (line.isEmpty())
+                continue;
+            // "noreply@cofidis.it (47 messages)" mentions the address before
+            // its count.
+            mentioned.insert(line.section(QLatin1Char(' '), 0, 0).toLower());
+        }
+        existing.close();
+    }
+
+    QStringList additions;
+    for (auto it = counts.constBegin(); it != counts.constEnd(); ++it) {
+        const QString address = it.key().trimmed().toLower();
+        if (address.isEmpty() || mentioned.contains(address))
+            continue;
+        if (!looksLikeBulk(address))
+            continue;
+        additions.append(QStringLiteral("# %1 (%2 messages)")
+                             .arg(address)
+                             .arg(it.value()));
+    }
+    if (additions.isEmpty())
+        return;
+
+    additions.sort();
+
+    QDir().mkpath(QFileInfo(path).absolutePath());
+    QFile file(path);
+    if (!file.open(QIODevice::Append | QIODevice::Text))
+        return;
+    QTextStream out(&file);
+    for (const QString &line : additions)
+        out << line << '\n';
+}
+
+QString scanQuery(const QString &path)
+{
+    // "*" is notmuch's match-everything. An EMPTY string would also match
+    // everything, which is why Config::matchNothingQuery() exists elsewhere in
+    // this codebase; being explicit here means a reader never has to wonder
+    // which of the two an empty return meant.
+    const List existing = load(path);
+    if (existing.addresses.isEmpty() && existing.domains.isEmpty())
+        return QStringLiteral("*");
+    return QStringLiteral("date:1week..");
+}
+
 } // namespace BusinessSenders
diff --git a/src/businesssenders.h b/src/businesssenders.h
index 0689453..3065ae5 100644
--- a/src/businesssenders.h
+++ b/src/businesssenders.h
@@ -18,6 +18,7 @@
 
 #pragma once
 
+#include <QHash>
 #include <QSet>
 #include <QString>
 #include <QStringList>
@@ -55,4 +56,33 @@ bool contains(const List &list, const QString &address);
 /// QStandardPaths::GenericConfigLocation.
 QString defaultPath();
 
+/// True when a local part looks like bulk mail rather than a person.
+///
+/// A GUESS, and openly one. It misses senders and proposes wrong ones, which
+/// is exactly why nothing it produces takes effect until the user uncomments
+/// it.
+bool looksLikeBulk(const QString &address);
+
+/// Appends anything in `counts` that looks like bulk and is not already in the
+/// file, COMMENTED OUT, with its message count.
+///
+/// Two rules, both load-bearing. It never writes an uncommented entry, so
+/// nothing on screen changes until the user acts. And it skips an address
+/// already present in ANY form, commented or not, so an entry the user
+/// rejected is never re-proposed, and one they deleted only returns if that
+/// sender writes again.
+void appendCandidates(const QString &path, const QHash<QString, int> &counts);
+
+/// The query the candidate scan should run.
+///
+/// A week of mail once the file exists, so the step stays incremental and
+/// cheap. EVERYTHING when the file is missing or holds no entries, because
+/// that is the first run: a week's mail proposes almost nothing, and the file
+/// would then take months to become useful. The whole-database scan is
+/// affordable precisely because it happens once, measured at 76 ms over 5105
+/// messages.
+///
+/// Returns notmuch query syntax, which is wire format and is never translated.
+QString scanQuery(const QString &path);
+
 } // namespace BusinessSenders
diff --git a/tests/test_businesssenders.cpp b/tests/test_businesssenders.cpp
index 64a96fa..bc6a5f6 100644
--- a/tests/test_businesssenders.cpp
+++ b/tests/test_businesssenders.cpp
@@ -16,6 +16,7 @@
  * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
  */
 
+#include <QFileInfo>
 #include <QTemporaryDir>
 #include <QTest>
 
@@ -32,6 +33,11 @@ private slots:
     void whitespaceAroundAnEntryIsIgnored();
     void matchingIsCaseInsensitive();
     void anAbsentFileMatchesNothing();
+    void candidatesAreAppendedCommentedOut();
+    void anAddressAlreadyPresentIsNeverReproposed();
+    void onlyBulkLookingLocalPartsAreProposed();
+    void theFirstRunScansEverything();
+    void alaterRunScansOnlyRecentMail();
 };
 
 void TestBusinessSenders::anExactAddressMatches()
@@ -97,5 +103,99 @@ void TestBusinessSenders::anAbsentFileMatchesNothing()
     QVERIFY(!BusinessSenders::contains(list, QStringLiteral("a@example.org")));
 }
 
+void TestBusinessSenders::candidatesAreAppendedCommentedOut()
+{
+    QTemporaryDir dir;
+    const QString path = dir.filePath(QStringLiteral("business-senders"));
+
+    QHash<QString, int> counts;
+    counts.insert(QStringLiteral("noreply@cofidis.it"), 47);
+    BusinessSenders::appendCandidates(path, counts);
+
+    QFile file(path);
+    QVERIFY(file.open(QIODevice::ReadOnly | QIODevice::Text));
+    const QString written = QString::fromUtf8(file.readAll());
+
+    // Commented, and carrying the count so the user can judge it.
+    QVERIFY(written.contains(QStringLiteral("# noreply@cofidis.it")));
+    QVERIFY(written.contains(QStringLiteral("47")));
+
+    // Nothing it wrote may take effect on its own.
+    const BusinessSenders::List list = BusinessSenders::load(path);
+    QVERIFY(!BusinessSenders::contains(list,
+                                       QStringLiteral("noreply@cofidis.it")));
+}
+
+void TestBusinessSenders::anAddressAlreadyPresentIsNeverReproposed()
+{
+    QTemporaryDir dir;
+    const QString path = dir.filePath(QStringLiteral("business-senders"));
+
+    // Both forms count as present: an active entry and a rejected one. The
+    // rejected case is the one that matters, since re-proposing it would undo
+    // the user's decision every ten minutes with no explanation.
+    QFile seed(path);
+    QVERIFY(seed.open(QIODevice::WriteOnly | QIODevice::Text));
+    seed.write("billing@example.org\n# noreply@cofidis.it (47 messages)\n");
+    seed.close();
+    const qint64 sizeBefore = QFileInfo(path).size();
+
+    QHash<QString, int> counts;
+    counts.insert(QStringLiteral("noreply@cofidis.it"), 51);
+    counts.insert(QStringLiteral("billing@example.org"), 12);
+    BusinessSenders::appendCandidates(path, counts);
+
+    QCOMPARE(QFileInfo(path).size(), sizeBefore);
+}
+
+void TestBusinessSenders::onlyBulkLookingLocalPartsAreProposed()
+{
+    QTemporaryDir dir;
+    const QString path = dir.filePath(QStringLiteral("business-senders"));
+
+    QHash<QString, int> counts;
+    counts.insert(QStringLiteral("noreply@a.org"), 3);
+    counts.insert(QStringLiteral("john.doe@b.org"), 3);
+    BusinessSenders::appendCandidates(path, counts);
+
+    QFile file(path);
+    QVERIFY(file.open(QIODevice::ReadOnly | QIODevice::Text));
+    const QString written = QString::fromUtf8(file.readAll());
+    QVERIFY(written.contains(QStringLiteral("noreply@a.org")));
+    QVERIFY(!written.contains(QStringLiteral("john.doe@b.org")));
+}
+
+void TestBusinessSenders::theFirstRunScansEverything()
+{
+    QTemporaryDir dir;
+    const QString missing = dir.filePath(QStringLiteral("business-senders"));
+
+    // No file at all: a week of mail would propose almost nothing and the
+    // list would take months to become useful, so the first run pays for a
+    // full scan once.
+    QCOMPARE(BusinessSenders::scanQuery(missing), QStringLiteral("*"));
+
+    // A file holding ONLY rejected candidates is still a first run: nothing
+    // has been accepted yet. Rescanning re-proposes none of them, since
+    // appendCandidates skips anything already mentioned.
+    QFile rejected(missing);
+    QVERIFY(rejected.open(QIODevice::WriteOnly | QIODevice::Text));
+    rejected.write("# noreply@cofidis.it (47 messages)\n");
+    rejected.close();
+    QCOMPARE(BusinessSenders::scanQuery(missing), QStringLiteral("*"));
+}
+
+void TestBusinessSenders::alaterRunScansOnlyRecentMail()
+{
+    QTemporaryDir dir;
+    const QString path = dir.filePath(QStringLiteral("business-senders"));
+    QFile file(path);
+    QVERIFY(file.open(QIODevice::WriteOnly | QIODevice::Text));
+    file.write("billing@example.org\n");
+    file.close();
+
+    QCOMPARE(BusinessSenders::scanQuery(path), QStringLiteral("date:1week.."));
+}
+
 QTEST_MAIN(TestBusinessSenders)
 #include "test_businesssenders.moc"