forked from github/quartz
511b003da8
Introduces scripts/pipeline/, a Mix project that runs as a post-export transformation pass over content/*.md before Quartz builds the site. Pipeline (scripts/export.exs phase 3): - Compiles and loads the Mix project at export time (cached after first run) - Applies a list of Transform modules sequentially over all .md files - Only rewrites files that were actually changed Citations transform (Pipeline.Transforms.Citations): - Resolves [cite:@key] and bare cite:key syntax produced by ox-hugo/citar - Resolution chain: Zotero BBT JSON-RPC → BibTeX file → DOI/bare-key fallback - Zotero probe uses a no-op JSON-RPC call (cayw endpoint blocks indefinitely) - Zotero resolver fetches PDF attachments via item.attachments, producing zotero://open-pdf/... links; falls back to zotero://select/library/items/... - BibTeX resolver parses .bib files with a simple regex parser (no deps) - DOI resolver is the always-succeeding last resort Configuration via env vars: BIBTEX_FILE — path to .bib file for fallback resolution ZOTERO_URL — Zotero base URL (default: http://localhost:23119) CITATION_MODE — silent | warn (default) | strict Adding future transforms requires only implementing Pipeline.Transform behaviour and appending the module to the transforms list in export.exs.
84 lines
2.6 KiB
Elixir
84 lines
2.6 KiB
Elixir
defmodule Pipeline do
|
|
@moduledoc """
|
|
Post-export markdown transformation pipeline.
|
|
|
|
Applies a list of transform modules sequentially over every .md file
|
|
in a content directory. Each transform module must implement:
|
|
|
|
apply(content :: String.t(), opts :: map()) :: String.t()
|
|
|
|
Transforms are applied in the order given. A file is rewritten only
|
|
when at least one transform mutates its content (checked via equality).
|
|
|
|
## Usage
|
|
|
|
opts = %{
|
|
zotero_url: "http://localhost:23119",
|
|
bibtex_file: System.get_env("BIBTEX_FILE"),
|
|
citation_mode: :warn # :silent | :warn | :strict
|
|
}
|
|
|
|
Pipeline.run(content_dir, [Pipeline.Transforms.Citations], opts)
|
|
"""
|
|
|
|
require Logger
|
|
|
|
@type transform :: module()
|
|
@type opts :: map()
|
|
|
|
@doc """
|
|
Run all transforms over every .md file under `content_dir`.
|
|
Returns `{:ok, stats}` where stats maps each transform to a count of files it changed.
|
|
"""
|
|
@spec run(String.t(), [transform()], opts()) :: {:ok, map()}
|
|
def run(content_dir, transforms, opts \\ %{}) do
|
|
md_files =
|
|
content_dir
|
|
|> Path.join("**/*.md")
|
|
|> Path.wildcard()
|
|
|
|
if md_files == [] do
|
|
Logger.warning("Pipeline: no .md files found in #{content_dir}")
|
|
{:ok, %{}}
|
|
else
|
|
Logger.info("Pipeline: processing #{length(md_files)} markdown files with #{length(transforms)} transform(s)")
|
|
|
|
# Initialise transforms (allows them to perform setup such as loading a .bib file).
|
|
# Each transform module must implement the Pipeline.Transform behaviour.
|
|
initialized =
|
|
Enum.map(transforms, fn mod ->
|
|
state = mod.init(opts)
|
|
{mod, state}
|
|
end)
|
|
|
|
stats =
|
|
Enum.reduce(md_files, %{}, fn path, acc ->
|
|
original = File.read!(path)
|
|
|
|
{transformed, file_stats} =
|
|
Enum.reduce(initialized, {original, %{}}, fn {mod, state}, {content, fstats} ->
|
|
result = mod.apply(content, state, opts)
|
|
changed = result != content
|
|
{result, Map.update(fstats, mod, (if changed, do: 1, else: 0), &(&1 + (if changed, do: 1, else: 0)))}
|
|
end)
|
|
|
|
if transformed != original do
|
|
File.write!(path, transformed)
|
|
Logger.debug("Pipeline: updated #{Path.relative_to_cwd(path)}")
|
|
end
|
|
|
|
Map.merge(acc, file_stats, fn _k, a, b -> a + b end)
|
|
end)
|
|
|
|
Enum.each(initialized, fn {mod, state} ->
|
|
# teardown/1 is optional in the behaviour
|
|
if function_exported?(mod, :teardown, 1) do
|
|
mod.teardown(state)
|
|
end
|
|
end)
|
|
|
|
{:ok, stats}
|
|
end
|
|
end
|
|
end
|