Jeffrey Ward
fac3adbaf6
Text files sorted by stage 3 now flow onto a new work queue and worker pool that enrich them with natural language (Languages.jl LanguageDetector: name, ISO 639-3 code, confidence) and programming language (github-linguist), writing a .meta.json sidecar to data/text_done/ like the stage-2 known-file pipeline. github-linguist reads the git blob of a path inside a repo, so untracked data/ files are copied to /tmp (outside any repo, name preserved for extension heuristics) before detection. Programming-language lookup is best-effort (startup warning if missing, degraded/null on failure); natural-language failure yields a degraded sidecar, not a quarantine. Factored exiftool's timeout-kill into shared run_with_timeout and the durable sidecar-first commit into commit_enriched!, both reused by stage 4. Recovery re-drives data/text/; graceful drain closes the text queue after its stage-3 producers finish.
363 lines
16 KiB
Julia
363 lines
16 KiB
Julia
using Test
|
||
using FileServer
|
||
using JSON3
|
||
|
||
# Pull internals into scope. These aren't exported (only `run` is), but the
|
||
# whole risk profile of this pipeline lives in these functions, so we test them
|
||
# directly rather than only through the HTTP surface.
|
||
using FileServer: Job, Config, ChannelQueue, enqueue!, dequeue!, length,
|
||
sanitize_filename, recover_dir!, normalize_metadata,
|
||
build_metadata, finalize_known!, run_exiftool,
|
||
is_binary, handle_unknown_job,
|
||
detect_natural_language, run_linguist, detect_programming_language,
|
||
read_text_sample, build_text_metadata, finalize_text!, handle_text_job,
|
||
linguist_available
|
||
using Languages: LanguageDetector
|
||
|
||
# A minimal, valid 1×1 PNG. Lets the real-exiftool tests assert stable facts
|
||
# (FileType == "PNG", 1×1 dimensions) that don't drift across exiftool versions.
|
||
const PNG_1x1 = UInt8[137,80,78,71,13,10,26,10,0,0,0,13,73,72,68,82,0,0,0,1,0,
|
||
0,0,1,8,6,0,0,0,31,21,196,137,0,0,0,11,73,68,65,84,120,218,99,100,248,255,
|
||
191,30,0,5,132,2,127,194,91,30,42,0,0,0,0,73,69,78,68,174,66,96,130]
|
||
|
||
"Build a Config whose data dirs all live under a fresh temp directory."
|
||
function tmp_config(root; kwargs...)
|
||
cfg = Config(;
|
||
spool_dir = joinpath(root, "spool"),
|
||
known_dir = joinpath(root, "known"),
|
||
unknown_dir = joinpath(root, "unknown"),
|
||
binary_dir = joinpath(root, "binary"),
|
||
text_dir = joinpath(root, "text"),
|
||
done_dir = joinpath(root, "done"),
|
||
text_done_dir = joinpath(root, "text_done"),
|
||
failed_dir = joinpath(root, "failed"),
|
||
kwargs...,
|
||
)
|
||
FileServer.ensure_dirs(cfg)
|
||
return cfg
|
||
end
|
||
|
||
@testset "FileServer" begin
|
||
|
||
@testset "sanitize_filename" begin
|
||
@test sanitize_filename("report.pdf") == "report.pdf"
|
||
# Directory components and traversal are stripped, not preserved.
|
||
@test sanitize_filename("../../etc/passwd") == "passwd"
|
||
@test sanitize_filename("/abs/path/x.txt") == "x.txt"
|
||
# Leading dots removed so "..", ".hidden" can't sneak through.
|
||
@test sanitize_filename("..") == "unnamed"
|
||
@test sanitize_filename(".hidden") == "hidden"
|
||
# Unsafe chars collapse to underscores; empty falls back to "unnamed".
|
||
@test sanitize_filename("a b&c*.d") == "a_b_c_.d"
|
||
@test sanitize_filename("") == "unnamed"
|
||
# Length is capped.
|
||
@test Base.length(sanitize_filename("a"^500)) == FileServer.MAX_NAME_LEN
|
||
end
|
||
|
||
@testset "normalize_metadata" begin
|
||
job = Job("id-1", "photo.jpg", "/data/known/id-1-photo.jpg", 4242, 0.0)
|
||
# Group-prefixed tags as exiftool -G emits them are already group-stripped
|
||
# by run_exiftool before reaching normalize_metadata, so keys are bare.
|
||
bytag = Dict{String,Any}(
|
||
"FileType" => "JPEG",
|
||
"MIMEType" => "image/jpeg",
|
||
"ImageWidth" => 800,
|
||
"ImageHeight"=> 600,
|
||
"Author" => "Ada Lovelace",
|
||
"Creator" => "Acrobat", # feeds created_by, not author
|
||
"CreateDate" => "2020:01:02 03:04:05",
|
||
"ModifyDate" => "2020:01:02 03:04:06",
|
||
"PageCount" => 12,
|
||
)
|
||
m = normalize_metadata(job, bytag)
|
||
@test m.file_type == "JPEG"
|
||
@test m.mime_type == "image/jpeg"
|
||
@test m.dimensions == (width = 800, height = 600)
|
||
@test m.author == "Ada Lovelace"
|
||
@test m.created_by == "Acrobat"
|
||
@test m.created_date == "2020:01:02 03:04:05"
|
||
@test m.page_count == 12
|
||
@test m.error === nothing
|
||
@test m.raw === bytag
|
||
# file_size is authoritative from the Job, never from exiftool.
|
||
@test m.file_size == 4242
|
||
end
|
||
|
||
@testset "normalize_metadata: missing tags degrade to nothing" begin
|
||
job = Job("id-2", "blob.bin", "/data/known/id-2-blob.bin", 7, 0.0)
|
||
m = normalize_metadata(job, Dict{String,Any}())
|
||
@test m.file_type === nothing
|
||
@test m.dimensions === nothing # neither width nor height present
|
||
@test m.author === nothing
|
||
@test m.file_size == 7
|
||
@test m.error === nothing # empty-but-present dict is still "success"
|
||
end
|
||
|
||
@testset "build_metadata: degraded on extraction failure" begin
|
||
mktempdir() do root
|
||
cfg = tmp_config(root; exiftool_timeout=5)
|
||
# Point at a nonexistent file → exiftool exits non-zero → degraded.
|
||
job = Job("id-3", "gone.dat", joinpath(cfg.known_dir, "id-3-gone.dat"), 99, 0.0)
|
||
m = build_metadata(job, cfg)
|
||
@test m.error !== nothing
|
||
@test m.file_type === nothing
|
||
@test m.raw === nothing
|
||
@test m.file_size == 99 # still authoritative from the Job
|
||
@test m.id == "id-3"
|
||
end
|
||
end
|
||
|
||
@testset "run_exiftool: real extraction on a PNG" begin
|
||
mktempdir() do root
|
||
p = joinpath(root, "pixel.png")
|
||
write(p, PNG_1x1)
|
||
bytag = run_exiftool(p, 30)
|
||
@test bytag !== nothing
|
||
@test bytag["FileType"] == "PNG"
|
||
@test bytag["ImageWidth"] == 1
|
||
@test bytag["ImageHeight"] == 1
|
||
end
|
||
end
|
||
|
||
@testset "finalize_known!: sidecar-first commit, end to end" begin
|
||
mktempdir() do root
|
||
cfg = tmp_config(root)
|
||
# A real known-stage file to enrich.
|
||
src = joinpath(cfg.known_dir, "id-9-pixel.png")
|
||
write(src, PNG_1x1)
|
||
job = Job("id-9", "pixel.png", src, Base.length(PNG_1x1), 0.0)
|
||
|
||
meta = build_metadata(job, cfg)
|
||
file_dest, sidecar = finalize_known!(cfg, job, meta)
|
||
|
||
# File moved into done/, original gone from known/.
|
||
@test isfile(file_dest)
|
||
@test dirname(file_dest) == cfg.done_dir
|
||
@test !isfile(src)
|
||
|
||
# Sidecar committed alongside it, valid JSON, no leftover .tmp.
|
||
@test isfile(sidecar)
|
||
@test endswith(sidecar, ".meta.json")
|
||
@test !isfile(string(sidecar, ".tmp"))
|
||
parsed = JSON3.read(read(sidecar, String))
|
||
@test parsed.file_type == "PNG"
|
||
@test parsed.file_size == Base.length(PNG_1x1)
|
||
@test parsed.error === nothing
|
||
end
|
||
end
|
||
|
||
@testset "is_binary: UTF-8 sniff" begin
|
||
mktempdir() do root
|
||
# Plain ASCII text → text.
|
||
txt = joinpath(root, "notes.txt")
|
||
write(txt, "hello, world\nsecond line\n")
|
||
@test is_binary(txt) == false
|
||
|
||
# Non-ASCII UTF-8 (accents, CJK, emoji) is valid text — the whole
|
||
# point of moving off the printable-ASCII/NUL heuristic.
|
||
uni = joinpath(root, "unicode.txt")
|
||
write(uni, "café — 日本語 — 🚀\n")
|
||
@test is_binary(uni) == false
|
||
|
||
# ANSI-colored log: ESC + other text control bytes are text-safe.
|
||
ansi = joinpath(root, "colored.log")
|
||
write(ansi, "\e[31merror\e[0m: tab\there\r\nnext\n")
|
||
@test is_binary(ansi) == false
|
||
|
||
# A NUL byte anywhere in the sniff window → binary (it's a control
|
||
# byte outside the text-safe set, even though it's valid UTF-8).
|
||
bin = joinpath(root, "blob.dat")
|
||
write(bin, UInt8[0x01, 0x02, 0x00, 0x03])
|
||
@test is_binary(bin) == true
|
||
|
||
# A non-NUL, non-text control byte (e.g. 0x07 BEL) → binary.
|
||
ctrl = joinpath(root, "ctrl.dat")
|
||
write(ctrl, UInt8[UInt8('h'), UInt8('i'), 0x07])
|
||
@test is_binary(ctrl) == true
|
||
|
||
# Malformed UTF-8 (lone continuation / bad lead byte) → binary.
|
||
bad = joinpath(root, "bad.dat")
|
||
write(bad, UInt8[UInt8('a'), 0xff, 0xfe, 0xc3, 0x28])
|
||
@test is_binary(bad) == true
|
||
|
||
# A multi-byte char split by the sniff boundary must NOT read as
|
||
# binary: pad to one byte short of the window, then a 2-byte 'é'
|
||
# (0xc3 0xa9) so only its lead byte lands inside the window.
|
||
split = joinpath(root, "split.txt")
|
||
write(split, vcat(fill(UInt8('a'), FileServer.CONTENT_SNIFF_BYTES - 1),
|
||
UInt8[0xc3, 0xa9]))
|
||
@test is_binary(split) == false
|
||
|
||
# Empty file → treated as text.
|
||
empty = joinpath(root, "empty")
|
||
write(empty, UInt8[])
|
||
@test is_binary(empty) == false
|
||
|
||
# Binary garbage past the sniff window is not seen → still text.
|
||
far = joinpath(root, "far.txt")
|
||
write(far, vcat(fill(UInt8('a'), FileServer.CONTENT_SNIFF_BYTES), UInt8[0x00]))
|
||
@test is_binary(far) == false
|
||
end
|
||
end
|
||
|
||
@testset "handle_unknown_job: binary terminal, text routed to stage 4" begin
|
||
mktempdir() do root
|
||
cfg = tmp_config(root)
|
||
text_queue = ChannelQueue(10)
|
||
|
||
# A binary file (embedded NUL) lands in binary/ and is NOT enqueued.
|
||
bpath = joinpath(cfg.unknown_dir, "id-b-blob.dat")
|
||
write(bpath, UInt8[0x00, 0xFF, 0x10])
|
||
bjob = Job("id-b", "blob.dat", bpath, filesize(bpath), 0.0)
|
||
handle_unknown_job(bjob, cfg, 1, text_queue)
|
||
@test isfile(joinpath(cfg.binary_dir, "id-b-blob.dat"))
|
||
@test !isfile(bpath)
|
||
@test length(text_queue) == 0
|
||
|
||
# A text file lands in text/ AND is routed onto the stage-4 queue,
|
||
# with its path updated to the new text/ location.
|
||
tpath = joinpath(cfg.unknown_dir, "id-t-notes.log")
|
||
write(tpath, "just some log text\n")
|
||
tjob = Job("id-t", "notes.log", tpath, filesize(tpath), 0.0)
|
||
handle_unknown_job(tjob, cfg, 1, text_queue)
|
||
moved = joinpath(cfg.text_dir, "id-t-notes.log")
|
||
@test isfile(moved)
|
||
@test !isfile(tpath)
|
||
@test length(text_queue) == 1
|
||
routed = dequeue!(text_queue)
|
||
@test routed.id == "id-t"
|
||
@test routed.path == moved
|
||
end
|
||
end
|
||
|
||
@testset "detect_natural_language" begin
|
||
d = LanguageDetector()
|
||
name, code, conf = detect_natural_language(d,
|
||
"The quick brown fox jumps over the lazy dog and then runs away quickly today.")
|
||
@test name == "English"
|
||
@test code == "eng"
|
||
@test conf isa Real && 0.0 <= conf <= 1.0
|
||
|
||
# Empty / whitespace-only text yields no result rather than throwing
|
||
# (the detector itself errors on empty input).
|
||
@test detect_natural_language(d, "") == (nothing, nothing, nothing)
|
||
@test detect_natural_language(d, " \n\t ") == (nothing, nothing, nothing)
|
||
end
|
||
|
||
@testset "read_text_sample: bounded, UTF-8 safe" begin
|
||
mktempdir() do root
|
||
p = joinpath(root, "notes.txt")
|
||
write(p, "café — 日本語 — hello\n")
|
||
@test read_text_sample(p) == "café — 日本語 — hello\n"
|
||
|
||
# Reads at most LANG_SAMPLE_BYTES, and doesn't choke on a multi-byte
|
||
# char straddling that boundary (trailing 'é' half-in the window).
|
||
big = joinpath(root, "big.txt")
|
||
write(big, vcat(fill(UInt8('a'), FileServer.LANG_SAMPLE_BYTES - 1),
|
||
UInt8[0xc3, 0xa9])) # 'é' split by the edge
|
||
s = read_text_sample(big)
|
||
@test Base.length(s) == FileServer.LANG_SAMPLE_BYTES - 1 # trailing half-char trimmed
|
||
@test all(==('a'), s)
|
||
end
|
||
end
|
||
|
||
@testset "run_linguist: real detection on source vs. prose" begin
|
||
if !linguist_available()
|
||
@info "github-linguist not on PATH; skipping run_linguist tests"
|
||
else
|
||
mktempdir() do root
|
||
# A Python source file → linguist names the language.
|
||
py = joinpath(root, "script.py")
|
||
write(py, "import sys\ndef main():\n print('hi')\nmain()\n")
|
||
@test run_linguist(py, 30) == "Python"
|
||
|
||
# Plain prose reports as "Text", which collapses to nothing.
|
||
prose = joinpath(root, "notes.txt")
|
||
write(prose, "The quarterly report shows steady growth this year.\n")
|
||
@test run_linguist(prose, 30) === nothing
|
||
end
|
||
end
|
||
end
|
||
|
||
@testset "build_text_metadata + finalize_text!: end to end" begin
|
||
mktempdir() do root
|
||
cfg = tmp_config(root)
|
||
d = LanguageDetector()
|
||
|
||
src = joinpath(cfg.text_dir, "id-x-script.py")
|
||
write(src, join(["# a short program in English prose comment",
|
||
"import sys",
|
||
"def greet(name):",
|
||
" print('hello ' + name + ' welcome to the show today')",
|
||
"greet('world')", ""], "\n"))
|
||
job = Job("id-x", "script.py", src, filesize(src), 0.0)
|
||
|
||
meta = build_text_metadata(d, job, cfg)
|
||
@test meta.id == "id-x"
|
||
@test meta.content_type == "text"
|
||
@test meta.file_size == filesize(src)
|
||
@test meta.language !== nothing # some natural language detected
|
||
@test meta.error === nothing
|
||
# programming_language is best-effort; present only when linguist is.
|
||
if linguist_available()
|
||
@test meta.programming_language == "Python"
|
||
end
|
||
|
||
file_dest, sidecar = finalize_text!(cfg, job, meta)
|
||
# File moved into text_done/, original gone from text/.
|
||
@test isfile(file_dest)
|
||
@test dirname(file_dest) == cfg.text_done_dir
|
||
@test !isfile(src)
|
||
# Sidecar committed alongside it, valid JSON, no leftover .tmp.
|
||
@test isfile(sidecar)
|
||
@test endswith(sidecar, ".meta.json")
|
||
@test !isfile(string(sidecar, ".tmp"))
|
||
parsed = JSON3.read(read(sidecar, String))
|
||
@test parsed.content_type == "text"
|
||
@test parsed.file_size == filesize(file_dest)
|
||
end
|
||
end
|
||
|
||
@testset "handle_text_job: enriches and commits to text_done/" begin
|
||
mktempdir() do root
|
||
cfg = tmp_config(root)
|
||
d = LanguageDetector()
|
||
|
||
src = joinpath(cfg.text_dir, "id-h-readme.md")
|
||
write(src, "# Project\n\nThis project does something useful and interesting for everyone.\n")
|
||
job = Job("id-h", "readme.md", src, filesize(src), 0.0)
|
||
|
||
handle_text_job(job, cfg, 1, d)
|
||
@test isfile(joinpath(cfg.text_done_dir, "id-h-readme.md"))
|
||
@test isfile(joinpath(cfg.text_done_dir, "id-h-readme.md.meta.json"))
|
||
@test !isfile(src)
|
||
end
|
||
end
|
||
|
||
@testset "recover_dir!: re-enqueues work, skips sidecars" begin
|
||
mktempdir() do root
|
||
dir = joinpath(root, "known"); mkpath(dir)
|
||
uuid = "0123456789abcdef0123456789abcdef0123" # 36 chars
|
||
work = joinpath(dir, string(uuid, "-report.pdf"))
|
||
write(work, "x")
|
||
write(joinpath(dir, string(uuid, "-report.pdf.meta.json")), "{}") # sidecar
|
||
write(joinpath(dir, "shortname"), "y") # no uuid prefix
|
||
|
||
q = ChannelQueue(10)
|
||
n = recover_dir!(dir, q)
|
||
@test n == 2 # the two real files, not the sidecar
|
||
@test length(q) == 2
|
||
|
||
jobs = [dequeue!(q), dequeue!(q)] # sorted by filename on recovery
|
||
# "0123...-report.pdf" sorts before "shortname".
|
||
@test jobs[1].id == uuid
|
||
@test jobs[1].original_name == "report.pdf"
|
||
@test jobs[1].path == work
|
||
# File with no uuid prefix keeps its whole name; gets a minted id.
|
||
@test jobs[2].original_name == "shortname"
|
||
@test !isempty(jobs[2].id)
|
||
end
|
||
end
|
||
|
||
end
|