Merge pull request #2 from JuliaDocs/new-toml-header

Revise TOML format

Author: goerz

.typos.toml

@@ -0,0 +1,9 @@
+[default]
+extend-ignore-identifiers-re = [
+    "[A-Z]T",
+    "[0-9abcdef]{8}",
+    "[A-Z][a-z]+[A-Z]{2,5}[0-9]{4}",
+]
+
+[files]
+extend-exclude = ["*.bib", "*.toml", "test_inventory.jl"]

docs/src/formats.md

@@ -35,23 +35,24 @@ Note that `DocInventories` internally uses the `text/x-intersphinx` MIME type fo
 
 ## TOML Format
 
-The TOML format is another text output format that is optimized for human readability. It starts with a header section of the form
+The TOML format is a text output format that is optimized for human readability. It starts with a header section of the form
 
-```
-[Inventory]
-format = "DocInventories v0"
+```toml
+# DocInventory version 0
 project = "<project>"
 version = "<version>"
 ```
 
-The `format` line is mandatory and identifies the file as containing inventory data in the format described here.
+The comment in the first line is mandatory and identifies the file as containing inventory data in the format described here.
 
 !!! warning
-    As indicated by the `v0` in the `format` line, the format described here is currently experimental and may change without notice
+    As indicated by the "version 0" in the header comment line, the format described here is currently experimental and may change without notice
+
+The `project` line must specify the name of the project described by the inventory. It is mandatory. The `version` line may specify the version of the project. It is optional, but recommended.
 
 After that, each [`InventoryItem`](@ref) is represented by a multi-line block of the form
 
-```
+```toml
 [[<domain>.<role>]]
 name = "<name>"
 uri = "<uri>"
@@ -61,7 +62,7 @@ priority = <priority>
 
 The four lines for `name`, `uri`, `dispname`, and `priority` may occur in any order. Also, for items with the default priority (`-1` for the `std` domain, `1` otherwise), the `priority` line may be omitted. If `dispname` is equal to `name` (usually indicated by `dispname="-"`), the `dispname` line may also be omitted.
 
-The item-blocks may be grouped/separated by blank lines. In `.toml` file generated by `DocInventories.save("inventory.toml", inventory)` items will be grouped into blocks with the same `[[<domain>.<role>]]` with a blank line between each block.
+The item-blocks may be grouped/separated by blank lines. In `.toml` files generated by `DocInventories.save("inventory.toml", inventory)` items will be grouped into blocks with the same `[[<domain>.<role>]]` with a blank line between each block.
 
 Any TOML parser should read a `.toml` file with the above structure into a nested dictionary, so that `item_dict = toml_data[domain][role][i]` corresponds to the `i`'th inventory item with the given `domain` and `role`. That `item_dict` will then map `"name"`, `"uri"`, and potentially `"dispname"` and `"priority"` to their respective values.
 

docs/src/inventories/Documenter.toml

@@ -1,5 +1,4 @@
-[Inventory]
-format = "DocInventories v0"
+# DocInventory version 0
 project = "Documenter.jl"
 version = "1.2.1"
 

docs/src/inventories/Julia.toml

@@ -1,5 +1,5 @@
-[Inventory]
-format = "DocInventories v0"
+# DocInventory version 0
+
 project = "The Julia Language"
 version = "1.10.0"
 

docs/src/inventories/JuliaDocs.toml

@@ -1,7 +1,5 @@
-[Inventory]
-format = "DocInventories v0"
+# DocInventory version 0
 project = "JuliaDocs"
-version = ""
 
 [[std.doc]]
 name = "DocumenterInterLinks"

src/toml_format.jl

@@ -25,47 +25,50 @@ function Base.show(io::IO, ::MIME"application/toml", inventory::Inventory)
         push!(domains[item.domain][item.role], item_data)
     end
 
-    toml_dict = Dict(
-        "Inventory" => Dict(
-            "format" => "DocInventories v0",
-            "project" => inventory.project,
-            "version" => inventory.version,
-        ),
-        domains...
-    )
+    toml_dict = Dict("project" => inventory.project, domains...)
+    if !isempty(inventory.version)
+        toml_dict["version"] = inventory.version
+    end
 
+    TOML.println(io, "# DocInventory version 0")
     TOML.print(io, toml_dict; sorted=true)
 
 end
 
 
 function read_inventory(io::IO, ::MIME"application/toml")
+    format_header = readline(io)
+    if !startswith(format_header, "#")
+        @warn "Invalid format_header: $format_header"
+        # TODO: verify format_header more strictly once the format has settled.
+    end
     data = TOML.parse(io)
     try
-        inventory_format = data["Inventory"]["format"]
-        if inventory_format != "DocInventories v0"
-            msg = "Invalid inventory format: $(repr(inventory_format))"
-            throw(InventoryFormatError(msg))
-        end
-        project = data["Inventory"]["project"]
-        version = data["Inventory"]["version"]
+        project = string(pop!(data, "project"))   # mandatory
+        version = string(pop!(data, "version", ""))  # optional
         items = InventoryItem[]
         for (domain, domain_data) in data
-            (domain == "Inventory") && continue  # that's the header, not a domain
-            for (role, role_data) in domain_data
-                for item_data in role_data
-                    push!(
-                        items,
-                        InventoryItem(
-                            item_data["name"],
-                            domain,
-                            role,
-                            get(item_data, "priority", (domain == "std") ? -1 : 1),
-                            item_data["uri"],
-                            get(item_data, "dispname", "-")
+            if domain_data isa Dict
+                for (role, role_data) in domain_data
+                    for item_data in role_data
+                        push!(
+                            items,
+                            InventoryItem(
+                                item_data["name"],
+                                domain,
+                                role,
+                                get(item_data, "priority", (domain == "std") ? -1 : 1),
+                                item_data["uri"],
+                                get(item_data, "dispname", "-")
+                            )
                         )
-                    )
+                    end
                 end
+            elseif domain == "format"
+                # For backward-compatibility, remove this `elseif` in v1.0
+                @warn "Unexpected key: $domain"
+            else
+                throw(InventoryFormatError("Unexpected key: $domain"))
             end
         end
         return project, version, items

test/test_inventory.jl

@@ -181,6 +181,118 @@ end
         @test c.value isa InventoryFormatError
         @test contains(c.output, "Unexpected line")
 
+        filename = joinpath(tempdir, "missing_project.toml")
+        #!format: off
+        write(filename, """
+        # DocInventory version 0
+
+        [[std.doc]]
+        name = "DocumenterInterLinks"
+        uri = "DocumenterInterLinks.jl#readme"
+        """)
+        #!format: on
+        c = IOCapture.capture(rethrow=Union{}) do
+            Inventory(filename; root_url="")
+        end
+        @test c.value isa InventoryFormatError
+        @test contains(c.output, "key \"project\" not found")
+
+        filename = joinpath(tempdir, "old_format.toml")
+        #!format: off
+        write(filename, """
+        [Inventory]
+        format = "DocInventories v0"
+        project = "Test"
+        version = "0.1.0"
+
+        [[std.doc]]
+        name = "DocumenterInterLinks"
+        uri = "DocumenterInterLinks.jl#readme"
+        """)
+        #!format: on
+        c = IOCapture.capture(rethrow=Union{}) do
+            Inventory(filename; root_url="")
+        end
+        @test_broken c.value isa InventoryFormatError
+        @test contains(c.output, "Unexpected key: format")
+        @test contains(c.output, "Invalid format_header: [Inventory]")
+
+        filename = joinpath(tempdir, "old_format2.toml")
+        #!format: off
+        write(filename, """
+        # This is an old inventory file, and because of this comment, the
+        # `[Inventory]` won't be stripped as a format_header
+
+        [Inventory]
+        format = "DocInventories v0"
+        project = "Test"
+        version = "0.1.0"
+
+        [[std.doc]]
+        name = "DocumenterInterLinks"
+        uri = "DocumenterInterLinks.jl#readme"
+        """)
+        #!format: on
+        c = IOCapture.capture(rethrow=Union{}) do
+            Inventory(filename; root_url="")
+        end
+        @test c.value isa InventoryFormatError
+        @test contains(c.output, "key \"project\" not found")
+
+        filename = joinpath(tempdir, "no_header_line.toml")
+        #!format: off
+        write(filename, """
+        project = "Test"
+        version = "0.1.0"
+
+        [[std.doc]]
+        name = "DocumenterInterLinks"
+        uri = "DocumenterInterLinks.jl#readme"
+        """)
+        #!format: on
+        c = IOCapture.capture(rethrow=Union{}) do
+            Inventory(filename; root_url="")
+        end
+        @test c.value isa InventoryFormatError
+        @test contains(c.output, "Invalid format_header: project = \"Test\"")
+        @test contains(c.output, "key \"project\" not found")
+
+        filename = joinpath(tempdir, "typo1.toml")
+        #!format: off
+        write(filename, """
+        # DocInventory version 0
+        project = "Test"
+        verison = "0.1.0"
+
+        [[std.doc]]
+        name = "DocumenterInterLinks"
+        uri = "DocumenterInterLinks.jl#readme"
+        """)
+        #!format: on
+        c = IOCapture.capture(rethrow=Union{}) do
+            Inventory(filename; root_url="")
+        end
+        @test c.value isa InventoryFormatError
+        @test contains(c.output, "Unexpected key: verison")
+
+        filename = joinpath(tempdir, "typo2.toml")
+        #!format: off
+        write(filename, """
+        # DocInventory version 0
+        project = "Test"
+        version = "0.1.0"
+
+        [[std_doc]]
+        name = "DocumenterInterLinks"
+        uri = "DocumenterInterLinks.jl#readme"
+        """)
+        #!format: on
+        c = IOCapture.capture(rethrow=Union{}) do
+            Inventory(filename; root_url="")
+        end
+        @test c.value isa InventoryFormatError
+        @test contains(c.output, "Unexpected key: std_doc")
+
     end
 
 end
@@ -484,6 +596,37 @@ end
         @test contains(c.output, "Only v2 objects.inv files currently supported")
         @test c.value isa InventoryFormatError
 
+        filename = joinpath(tempdir, "wrong_version_type.toml")
+        #!format: off
+        write(filename, """
+        # DocInventory version 0
+        project = "Test"
+        version = 1.0
+
+        [[std.doc]]
+        name = "DocumenterInterLinks"
+        uri = "DocumenterInterLinks.jl#readme"
+        """)
+        #!format: on
+        readinv = Inventory(filename; root_url="")
+        # this still works because the float "1.0" is converted to string
+        @test readinv.version == "1.0"
+
+        filename = joinpath(tempdir, "future_header.toml")
+        #!format: off
+        write(filename, """
+        # Documenter Inventory version 1
+        project = "Test"
+        version = "1.0"
+
+        [[std.doc]]
+        name = "DocumenterInterLinks"
+        uri = "DocumenterInterLinks.jl#readme"
+        """)
+        #!format: on
+        readinv = Inventory(filename; root_url="")
+        @test readinv.project == "Test"
+
     end
 
 end