Files
Nim/tests/stdlib/tdochelpers.nim
Andrey Makarov 2620da9bf9 docgen: implement cross-document links (#20990)
* docgen: implement cross-document links

Fully implements https://github.com/nim-lang/RFCs/issues/125
Follow-up of: https://github.com/nim-lang/Nim/pull/18642 (for internal links)
and https://github.com/nim-lang/Nim/issues/20127.

Overview
--------

Explicit import-like directive is required, called `.. importdoc::`.
(the syntax is % RST, Markdown will use it for a while).

Then one can reference any symbols/headings/anchors, as if they
were in the local file (but they will be prefixed with a module name
or markup document in link text).
It's possible to reference anything from anywhere (any direction
in `.nim`/`.md`/`.rst` files).

See `doc/docgen.md` for full description.

Working is based on `.idx` files, hence one needs to generate
all `.idx` beforehand. A dedicated option `--index:only` is introduced
(and a separate stage for `--index:only` is added to `kochdocs.nim`).

Performance note
----------------

Full run for `./koch docs` now takes 185% of the time before this PR.
(After: 315 s, before: 170 s on my PC).
All the time seems to be spent on `--index:only` run, which takes
almost as much (85%) of normal doc run -- it seems that most time
is spent on file parsing, turning off HTML generation phase has not
helped much.
(One could avoid it by specifying list of files that can be referenced
and pre-processing only them. But it can become error-prone and I assume
that these linke will be **everywhere** in the repository anyway,
especially considering https://github.com/nim-lang/RFCs/issues/478.
So every `.nim`/`.md` file is processed for `.idx` first).

But that's all without significant part of repository converted to
cross-module auto links. To estimate impact I checked the time for
`doc`ing a few files (after all indexes have been generated), and
everywhere difference was **negligible**.
E.g. for `lib/std/private/osfiles.nim` that `importdoc`s large
`os.idx` and hence should have been a case with relatively large
performance impact, but:

* After: 0.59 s.
* Before: 0.59 s.

So Nim compiler works so slow that doc part basically does not matter :-)

Testing
-------

1) added `extlinks` test to `nimdoc/`
2) checked that `theindex.html` is still correct
2) fixed broken auto-links for modules that were derived from `os.nim`
   by adding appropriate ``importdoc``

Implementation note
-------------------

Parsing and formating of `.idx` entries is moved into a dedicated
`rstidx.nim` module from `rstgen.nim`.

`.idx` file format changed:

* fields are not escaped in most cases because we need original
  strings for referencing, not HTML ones
  (the exception is linkTitle for titles and headings).
  Escaping happens later -- on the stage of `rstgen` buildIndex, etc.
* all lines have fixed number of columns 6
* added discriminator tag as a first column,
  it always allows distinguish Nim/markup entries, titles/headings, etc.
  `rstgen` does not rely any more (in most cases) on ad-hoc logic
  to determine what type each entry is.
* there is now always a title entry added at the first line.
* add a line number as 6th column
* linkTitle (4th) column has a different format: before it was like
  `module: funcName()`, now it's `proc funcName()`.
  (This format is also propagated to `theindex.html` and search results,
  I kept it that way since I like it more though it's discussible.)
  This column is what used for Nim symbols resolution.
* also changed details on column format for headings and titles:
  "keyword" is original, "linkTitle" is HTML one

* fix paths on Windows + more clear code

* Update compiler/docgen.nim

Co-authored-by: Andreas Rumpf <rumpf_a@web.de>

* Handle .md and .nim paths uniformly in findRefFile

* handle titles better + more comments

* don't allow markup overwrite index title for .nim files

Co-authored-by: Andreas Rumpf <rumpf_a@web.de>
2023-01-04 15:19:01 -05:00

221 lines
8.9 KiB
Nim

discard """
output: '''
[Suite] Integration with Nim
'''
"""
# tests for dochelpers.nim module
import ../../lib/packages/docutils/[rstast, rst, dochelpers]
import unittest
import std/assertions
proc testMsgHandler(filename: string, line, col: int, msgkind: MsgKind,
arg: string) =
doAssert msgkind == mwBrokenLink
proc fromRst(text: string): LangSymbol =
let r = rstParse(text, "-input-", LineRstInit, ColRstInit,
{roNimFile},
msgHandler=testMsgHandler)
assert r.node.kind == rnRstRef
result = toLangSymbol(r.node)
proc fromMd(text: string): LangSymbol =
let r = rstParse(text, "-input-", LineRstInit, ColRstInit,
{roPreferMarkdown, roSupportMarkdown, roNimFile},
msgHandler=testMsgHandler)
assert r.node.kind == rnPandocRef
assert r.node.len == 2
# this son is the target:
assert r.node.sons[1].kind == rnInner
result = toLangSymbol(r.node.sons[1])
suite "Integration with Nim":
test "simple symbol parsing (shortest form)":
let expected = LangSymbol(symKind: "", name: "g")
check "g_".fromRst == expected
check "[g]".fromMd == expected
# test also alternative syntax variants of Pandoc Markdown:
check "[g][]".fromMd == expected
check "[this symbol][g]".fromMd == expected
test "simple symbol parsing (group of words)":
#let input1 = "`Y`_".rstParseTest
let expected1 = LangSymbol(symKind: "", name: "Y")
check "`Y`_".fromRst == expected1
check "[Y]".fromMd == expected1
# this means not a statement 'type', it's a backticked identifier `type`:
let expected2 = LangSymbol(symKind: "", name: "type")
check "`type`_".fromRst == expected2
check "[type]".fromMd == expected2
let expected3 = LangSymbol(symKind: "", name: "[]")
check "`[]`_".fromRst == expected3
# Markdown syntax for this case is NOT [[]]
check "[`[]`]".fromMd == expected3
let expected4 = LangSymbol(symKind: "", name: "Xyz")
check "`X Y Z`_".fromRst == expected4
check "[X Y Z]".fromMd == expected4
test "simple proc parsing":
let expected = LangSymbol(symKind: "proc", name: "f")
check "`proc f`_".fromRst == expected
check "[proc f]".fromMd == expected
test "another backticked name":
let expected = LangSymbol(symKind: "template", name: "type")
check """`template \`type\``_""".fromRst == expected
# no backslash in Markdown:
check """[template `type`]""".fromMd == expected
test "simple proc parsing with parameters":
let expected = LangSymbol(symKind: "proc", name: "f",
parametersProvided: true)
check "`proc f*()`_".fromRst == expected
check "`proc f()`_".fromRst == expected
check "[proc f*()]".fromMd == expected
check "[proc f()]".fromMd == expected
test "symbol parsing with 1 parameter":
let expected = LangSymbol(symKind: "", name: "f",
parameters: @[("G[int]", "")],
parametersProvided: true)
check "`f(G[int])`_".fromRst == expected
check "[f(G[int])]".fromMd == expected
test "more proc parsing":
let input1 = "`proc f[T](x:G[T]):M[T]`_".fromRst
let input2 = "`proc f[ T ] ( x: G [T] ): M[T]`_".fromRst
let input3 = "`proc f*[T](x: G[T]): M[T]`_".fromRst
let expected = LangSymbol(symKind: "proc",
name: "f",
generics: "[T]",
parameters: @[("x", "G[T]")],
parametersProvided: true,
outType: "M[T]")
check(input1 == expected)
check(input2 == expected)
check(input3 == expected)
test "advanced proc parsing with Nim identifier normalization":
let inputRst = """`proc binarySearch*[T, K](a: openarray[T]; key: K;
cmp: proc (x: T; y: K): int)`_"""
let inputMd = """[proc binarySearch*[T, K](a: openarray[T]; key: K;
cmp: proc (x: T; y: K): int)]"""
let expected = LangSymbol(symKind: "proc",
name: "binarysearch",
generics: "[T,K]",
parameters: @[
("a", "openarray[T]"),
("key", "K"),
("cmp", "proc(x:T;y:K):int")],
parametersProvided: true,
outType: "")
check(inputRst.fromRst == expected)
check(inputMd.fromMd == expected)
test "the same without proc":
let input = """`binarySearch*[T, K](a: openarray[T]; key: K;
cmp: proc (x: T; y: K): int {.closure.})`_"""
let expected = LangSymbol(symKind: "",
name: "binarysearch",
generics: "[T,K]",
parameters: @[
("a", "openarray[T]"),
("key", "K"),
("cmp", "proc(x:T;y:K):int")],
parametersProvided: true,
outType: "")
check(input.fromRst == expected)
let inputMd = """[binarySearch*[T, K](a: openarray[T]; key: K;
cmp: proc (x: T; y: K): int {.closure.})]"""
check(inputMd.fromMd == expected)
test "operator $ with and without backticks":
let input1 = """`func \`$\`*[T](a: \`open Array\`[T]): string`_"""
let input1md = "[func `$`*[T](a: `open Array`[T]): string]"
let input2 = """`func $*[T](a: \`open Array\`[T]): string`_"""
let input2md = "[func $*[T](a: `open Array`[T]): string]"
let expected = LangSymbol(symKind: "func",
name: "$",
generics: "[T]",
parameters: @[("a", "openarray[T]")],
parametersProvided: true,
outType: "string")
check input1.fromRst == expected
check input2.fromRst == expected
check input1md.fromMd == expected
check input2md.fromMd == expected
test "operator [] with and without backticks":
let input1 = """`func \`[]\`[T](a: \`open Array\`[T], idx: int): T`_"""
let input1md = "[func `[]`[T](a: `open Array`[T], idx: int): T]"
let input2 = """`func [][T](a: \`open Array\`[T], idx: int): T`_"""
let input2md = "[func [][T](a: `open Array`[T], idx: int): T]"
let expected = LangSymbol(symKind: "func",
name: "[]",
generics: "[T]",
parameters: @[("a", "openarray[T]"),
("idx", "int")],
parametersProvided: true,
outType: "T")
check input1.fromRst == expected
check input2.fromRst == expected
check input1md.fromMd == expected
check input2md.fromMd == expected
test "postfix symbol specifier #1":
let input = "`walkDir iterator`_"
let inputMd = "[walkDir iterator]"
let expected = LangSymbol(symKind: "iterator",
name: "walkdir")
check input.fromRst == expected
check inputMd.fromMd == expected
test "postfix symbol specifier #2":
let input1 = """`\`[]\`[T](a: \`open Array\`[T], idx: int): T func`_"""
let input1md = "[`[]`[T](a: `open Array`[T], idx: int): T func]"
let input2 = """`[][T](a: \`open Array\`[T], idx: int): T func`_"""
# note again that ` is needed between 1st and second [
let input2md = "[`[]`[T](a: `open Array`[T], idx: int): T func]"
let expected = LangSymbol(symKind: "func",
name: "[]",
generics: "[T]",
parameters: @[("a", "openarray[T]"),
("idx", "int")],
parametersProvided: true,
outType: "T")
check input1.fromRst == expected
check input2.fromRst == expected
check input1md.fromMd == expected
check input2md.fromMd == expected
test "type of type":
let inputRst = "`CopyFlag enum`_"
let inputMd = "[CopyFlag enum]"
let expected = LangSymbol(symKind: "type",
symTypeKind: "enum",
name: "Copyflag")
check inputRst.fromRst == expected
check inputMd.fromMd == expected
test "prefixed module":
let inputRst = "`module std / paths`_"
let inputMd = "[module std / paths]"
let expected = LangSymbol(symKind: "module",
name: "std/paths")
check inputRst.fromRst == expected
check inputMd.fromMd == expected
test "postfixed module":
let inputRst = "`std / paths module`_"
let inputMd = "[std / paths module]"
let expected = LangSymbol(symKind: "module",
name: "std/paths")
check inputRst.fromRst == expected
check inputMd.fromMd == expected