Add CanonPath wrapper to represent canonicalized paths

src/libutil/canon-path.cc

@@ -0,0 +1,72 @@
+#include "canon-path.hh"
+#include "util.hh"
+
+namespace nix {
+
+CanonPath CanonPath::root = CanonPath("/");
+
+CanonPath::CanonPath(std::string_view raw)
+    : path(absPath((Path) raw, "/"))
+{ }
+
+CanonPath::CanonPath(std::string_view raw, const CanonPath & root)
+    : path(absPath((Path) raw, root.abs()))
+{ }
+
+std::optional<CanonPath> CanonPath::parent() const
+{
+    if (isRoot()) return std::nullopt;
+    return CanonPath(unchecked_t(), path.substr(0, path.rfind('/')));
+}
+
+CanonPath CanonPath::resolveSymlinks() const
+{
+    return CanonPath(unchecked_t(), canonPath(abs(), true));
+}
+
+bool CanonPath::isWithin(const CanonPath & parent) const
+{
+    return !(
+        path.size() < parent.path.size()
+        || path.substr(0, parent.path.size()) != parent.path
+        || (parent.path.size() > 1 && path.size() > parent.path.size()
+            && path[parent.path.size()] != '/'));
+}
+
+void CanonPath::extend(const CanonPath & x)
+{
+    if (x.isRoot()) return;
+    if (isRoot())
+        path += x.rel();
+    else
+        path += x.abs();
+}
+
+CanonPath CanonPath::operator + (const CanonPath & x) const
+{
+    auto res = *this;
+    res.extend(x);
+    return res;
+}
+
+void CanonPath::push(std::string_view c)
+{
+    assert(c.find('/') == c.npos);
+    if (!isRoot()) path += '/';
+    path += c;
+}
+
+CanonPath CanonPath::operator + (std::string_view c) const
+{
+    auto res = *this;
+    res.push(c);
+    return res;
+}
+
+std::ostream & operator << (std::ostream & stream, const CanonPath & path)
+{
+    stream << path.abs();
+    return stream;
+}
+
+}

src/libutil/canon-path.hh

@@ -0,0 +1,139 @@
+#pragma once
+
+#include <string>
+#include <optional>
+#include <cassert>
+#include <iostream>
+
+namespace nix {
+
+/* A canonical representation of a path. It ensures the following:
+
+   - It always starts with a slash.
+
+   - It never ends with a slash, except if the path is "/".
+
+   - A slash is never followed by a slash (i.e. no empty components).
+
+   - There are no components equal to '.' or '..'.
+
+   Note that the path does not need to correspond to an actually
+   existing path, and there is no guarantee that symlinks are
+   resolved.
+*/
+class CanonPath
+{
+    std::string path;
+
+public:
+
+    /* Construct a canon path from a non-canonical path. Any '.', '..'
+       or empty components are removed. */
+    CanonPath(std::string_view raw);
+
+    explicit CanonPath(const char * raw)
+        : CanonPath(std::string_view(raw))
+    { }
+
+    struct unchecked_t { };
+
+    CanonPath(unchecked_t _, std::string path)
+        : path(std::move(path))
+    { }
+
+    static CanonPath root;
+
+    /* If `raw` starts with a slash, return
+       `CanonPath(raw)`. Otherwise return a `CanonPath` representing
+       `root + "/" + raw`. */
+    CanonPath(std::string_view raw, const CanonPath & root);
+
+    bool isRoot() const
+    { return path.size() <= 1; }
+
+    explicit operator std::string_view() const
+    { return path; }
+
+    const std::string & abs() const
+    { return path; }
+
+    const char * c_str() const
+    { return path.c_str(); }
+
+    std::string_view rel() const
+    { return ((std::string_view) path).substr(1); }
+
+    struct Iterator
+    {
+        std::string_view remaining;
+        size_t slash;
+
+        Iterator(std::string_view remaining)
+            : remaining(remaining)
+            , slash(remaining.find('/'))
+        { }
+
+        bool operator != (const Iterator & x) const
+        { return remaining.data() != x.remaining.data(); }
+
+        const std::string_view operator * () const
+        { return remaining.substr(0, slash); }
+
+        void operator ++ ()
+        {
+            if (slash == remaining.npos)
+                remaining = remaining.substr(remaining.size());
+            else {
+                remaining = remaining.substr(slash + 1);
+                slash = remaining.find('/');
+            }
+        }
+    };
+
+    Iterator begin() { return Iterator(rel()); }
+    Iterator end() { return Iterator(rel().substr(path.size() - 1)); }
+
+    std::optional<CanonPath> parent() const;
+
+    std::optional<std::string_view> dirOf() const
+    {
+        if (isRoot()) return std::nullopt;
+        return path.substr(0, path.rfind('/'));
+    }
+
+    std::optional<std::string_view> baseName() const
+    {
+        if (isRoot()) return std::nullopt;
+        return ((std::string_view) path).substr(path.rfind('/') + 1);
+    }
+
+    bool operator == (const CanonPath & x) const
+    { return path == x.path; }
+
+    bool operator != (const CanonPath & x) const
+    { return path != x.path; }
+
+    bool operator < (const CanonPath & x) const
+    { return path < x.path; }
+
+    CanonPath resolveSymlinks() const;
+
+    /* Return true if `this` is equal to `parent` or a child of
+       `parent`. */
+    bool isWithin(const CanonPath & parent) const;
+
+    /* Append another path to this one. */
+    void extend(const CanonPath & x);
+
+    /* Concatenate two paths. */
+    CanonPath operator + (const CanonPath & x) const;
+
+    /* Add a path component to this one. It must not contain any slashes. */
+    void push(std::string_view c);
+
+    CanonPath operator + (std::string_view c) const;
+};
+
+std::ostream & operator << (std::ostream & stream, const CanonPath & path);
+
+}

src/libutil/fmt.hh

@@ -148,7 +148,7 @@ inline hintformat hintfmt(const std::string & fs, const Args & ... args)
     return f;
 }
 
-inline hintformat hintfmt(std::string plain_string)
+inline hintformat hintfmt(const std::string & plain_string)
 {
     // we won't be receiving any args in this case, so just print the original string
     return hintfmt("%s", normaltxt(plain_string));

src/libutil/tests/canon-path.cc

@@ -0,0 +1,98 @@
+#include "canon-path.hh"
+
+#include <gtest/gtest.h>
+
+namespace nix {
+
+    TEST(CanonPath, basic) {
+        {
+            CanonPath p("/");
+            ASSERT_EQ(p.abs(), "/");
+            ASSERT_EQ(p.rel(), "");
+            ASSERT_EQ(p.baseName(), std::nullopt);
+            ASSERT_EQ(p.dirOf(), std::nullopt);
+        }
+
+        {
+            CanonPath p("/foo//");
+            ASSERT_EQ(p.abs(), "/foo");
+            ASSERT_EQ(p.rel(), "foo");
+            ASSERT_EQ(*p.baseName(), "foo");
+            ASSERT_EQ(*p.dirOf(), ""); // FIXME: do we want this?
+        }
+
+        {
+            CanonPath p("foo/bar");
+            ASSERT_EQ(p.abs(), "/foo/bar");
+            ASSERT_EQ(p.rel(), "foo/bar");
+            ASSERT_EQ(*p.baseName(), "bar");
+            ASSERT_EQ(*p.dirOf(), "/foo");
+        }
+
+        {
+            CanonPath p("foo//bar/");
+            ASSERT_EQ(p.abs(), "/foo/bar");
+            ASSERT_EQ(p.rel(), "foo/bar");
+            ASSERT_EQ(*p.baseName(), "bar");
+            ASSERT_EQ(*p.dirOf(), "/foo");
+        }
+    }
+
+    TEST(CanonPath, iter) {
+        {
+            CanonPath p("a//foo/bar//");
+            std::vector<std::string_view> ss;
+            for (auto & c : p) ss.push_back(c);
+            ASSERT_EQ(ss, std::vector<std::string_view>({"a", "foo", "bar"}));
+        }
+
+        {
+            CanonPath p("/");
+            std::vector<std::string_view> ss;
+            for (auto & c : p) ss.push_back(c);
+            ASSERT_EQ(ss, std::vector<std::string_view>());
+        }
+    }
+
+    TEST(CanonPath, concat) {
+        {
+            CanonPath p1("a//foo/bar//");
+            CanonPath p2("xyzzy/bla");
+            ASSERT_EQ((p1 + p2).abs(), "/a/foo/bar/xyzzy/bla");
+        }
+
+        {
+            CanonPath p1("/");
+            CanonPath p2("/a/b");
+            ASSERT_EQ((p1 + p2).abs(), "/a/b");
+        }
+
+        {
+            CanonPath p1("/a/b");
+            CanonPath p2("/");
+            ASSERT_EQ((p1 + p2).abs(), "/a/b");
+        }
+
+        {
+            CanonPath p("/foo/bar");
+            ASSERT_EQ((p + "x").abs(), "/foo/bar/x");
+        }
+
+        {
+            CanonPath p("/");
+            ASSERT_EQ((p + "foo" + "bar").abs(), "/foo/bar");
+        }
+    }
+
+    TEST(CanonPath, within) {
+        {
+            ASSERT_TRUE(CanonPath("foo").isWithin(CanonPath("foo")));
+            ASSERT_FALSE(CanonPath("foo").isWithin(CanonPath("bar")));
+            ASSERT_FALSE(CanonPath("foo").isWithin(CanonPath("fo")));
+            ASSERT_TRUE(CanonPath("foo/bar").isWithin(CanonPath("foo")));
+            ASSERT_FALSE(CanonPath("foo").isWithin(CanonPath("foo/bar")));
+            ASSERT_TRUE(CanonPath("/foo/bar/default.nix").isWithin(CanonPath("/")));
+            ASSERT_TRUE(CanonPath("/").isWithin(CanonPath("/")));
+        }
+    }
+}

src/libutil/util.hh

@@ -721,4 +721,11 @@ inline std::string operator + (std::string && s, std::string_view s2)
     return s;
 }
 
+inline std::string operator + (std::string_view s1, const char * s2)
+{
+    std::string s(s1);
+    s.append(s2);
+    return s;
+}
+
 }