fix(demo_logs source): drop fakedata_generator, fix broken fake domains (#25236)

* fix(demo_logs source): drop fakedata_generator, fix broken fake domains

The fakedata_generator crate (v0.7.1) has an upstream bug: its
get_dataset() match table is missing a "tlds" arm, so gen_domain() falls
through to an empty JSON string. That fails to parse and the crate
prints "Failed getting dataset for tlds. EOF while parsing a value at
line 1 column 0" to stderr on every call, while gen_domain() returns
"<name>.Error: dataset not found" as the fake domain.

Drop the dependency (and its transitive passt dep) and inline the three
functions demo_logs actually used: gen_domain, gen_ipv4, gen_username.
Domains now look like "random.io" instead of "random.Error: dataset not
found", and stderr is quiet.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* chore(releasing): changelog fragment for demo_logs fakedata fix

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* chore(demo_logs source): drop stale comment, allow TLDs/fakedata in spelling

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* chore(demo_logs source): swap fake domain name list to unique entries

Replace the 8-word domain-name pool with fresh placeholder-style
entries so nothing in lib/fakedata derives from the fakedata_generator
crate's data.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

Author: pront

.github/actions/spelling/allow.txt

@@ -154,6 +154,7 @@ Evercoss
 exactlyonce
 Explay
 Fabro
+fakedata
 fakeintake
 FAQs
 fargate
@@ -509,6 +510,7 @@ timeseries
 timespan
 timestamped
 Tizen
+TLDs
 Tmobile
 tobz
 Tomtec

Cargo.lock

@@ -270,7 +270,6 @@ event-listener-strategy,https://github.com/smol-rs/event-listener-strategy,Apach
 evmap,https://github.com/jonhoo/rust-evmap,MIT OR Apache-2.0,Jon Gjengset <jon@thesquareplanet.com>
 evmap-derive,https://github.com/jonhoo/rust-evmap,MIT OR Apache-2.0,Jon Gjengset <jon@thesquareplanet.com>
 exitcode,https://github.com/benwilber/exitcode,Apache-2.0,Ben Wilber <benwilber@gmail.com>
-fakedata_generator,https://github.com/KevinGimbel/fakedata_generator,MIT,Kevin Gimbel <kevin@gimbel.dev>
 fallible-iterator,https://github.com/sfackler/rust-fallible-iterator,MIT OR Apache-2.0,Steven Fackler <sfackler@gmail.com>
 fancy-regex,https://github.com/fancy-regex/fancy-regex,MIT,"Raph Levien <raph@google.com>, Robin Stocker <robin@nibor.org>, Keith Hall <keith.hall@available.systems>"
 fastrand,https://github.com/smol-rs/fastrand,Apache-2.0 OR MIT,Stjepan Glavina <stjepang@gmail.com>
@@ -536,7 +535,6 @@ parking_lot,https://github.com/Amanieu/parking_lot,MIT OR Apache-2.0,Amanieu d'A
 parking_lot_core,https://github.com/Amanieu/parking_lot,MIT OR Apache-2.0,Amanieu d'Antras <amanieu@gmail.com>
 parquet,https://github.com/apache/arrow-rs,Apache-2.0,Apache Arrow <dev@arrow.apache.org>
 parse-size,https://github.com/kennytm/parse-size,MIT,kennytm <kennytm@gmail.com>
-passt,https://github.com/kevingimbel/passt,MIT OR Apache-2.0,Kevin Gimbel <hallo@kevingimbel.com>
 paste,https://github.com/dtolnay/paste,MIT OR Apache-2.0,David Tolnay <dtolnay@gmail.com>
 pastey,https://github.com/as1100k/pastey,MIT OR Apache-2.0,"Aditya Kumar <git@adityais.dev>, David Tolnay <dtolnay@gmail.com>"
 pbkdf2,https://github.com/RustCrypto/password-hashes/tree/master/pbkdf2,MIT OR Apache-2.0,RustCrypto Developers

LICENSE-3rdparty.csv

@@ -0,0 +1,9 @@
+The text content generated by the `demo_logs` source has changed: the
+pool of fake usernames and the pool of fake domain TLDs are now both
+defined inside Vector rather than pulled from an external crate. The
+line formats (`apache_common`, `apache_error`, `json`, `syslog`,
+`bsd_syslog`) are unchanged. If any of your tests or downstream
+pipelines assert on specific generated usernames or TLDs, please
+update those expectations.
+
+authors: pront

changelog.d/drop_fakedata_generator.fix.md

@@ -8,5 +8,4 @@ license = "MPL-2.0"
 
 [dependencies]
 chrono.workspace = true
-fakedata_generator = "0.7.1"
 rand.workspace = true

lib/fakedata/Cargo.toml

@@ -3,9 +3,44 @@ use chrono::{
     format::{DelayedFormat, StrftimeItems},
     prelude::Local,
 };
-use fakedata_generator::{gen_domain, gen_ipv4, gen_username};
 use rand::{Rng, rng};
 
+static FAKE_USERNAMES: [&str; 20] = [
+    "log_whisperer",
+    "commit_conductor",
+    "cache_cowboy",
+    "compile_captain",
+    "latency_llama",
+    "yaml_yoda",
+    "regex_rider",
+    "semver_sage",
+    "kernel_keith",
+    "pixel_pilgrim",
+    "kubectl_kev",
+    "pipeline_pat",
+    "telemetry_tina",
+    "merge_maria",
+    "parser_pete",
+    "debug_duchess",
+    "nullable_nate",
+    "grep_greg",
+    "stderr_stan",
+    "segfault_sue",
+];
+
+static FAKE_DOMAIN_NAMES: [&str; 8] = [
+    "acme",
+    "contoso",
+    "widgets",
+    "example",
+    "placeholder",
+    "sample",
+    "foobar",
+    "testbench",
+];
+
+static FAKE_DOMAIN_TLDS: [&str; 8] = ["com", "net", "org", "io", "dev", "co", "app", "biz"];
+
 static APPLICATION_NAMES: [&str; 10] = [
     "auth", "data", "deploy", "etl", "scraper", "cron", "ingress", "egress", "alerter", "fwd",
 ];
@@ -156,7 +191,11 @@ fn application() -> &'static str {
 }
 
 fn domain() -> String {
-    gen_domain()
+    format!(
+        "{}.{}",
+        random_from_array(&FAKE_DOMAIN_NAMES),
+        random_from_array(&FAKE_DOMAIN_TLDS),
+    )
 }
 
 fn error_level() -> &'static str {
@@ -188,7 +227,14 @@ fn http_version() -> &'static str {
 }
 
 fn ipv4_address() -> String {
-    gen_ipv4()
+    let mut r = rng();
+    format!(
+        "{}.{}.{}.{}",
+        r.random_range(1..255),
+        r.random_range(1..255),
+        r.random_range(1..255),
+        r.random_range(1..255),
+    )
 }
 
 fn pid() -> usize {
@@ -208,7 +254,7 @@ fn referer() -> String {
 }
 
 fn username() -> String {
-    gen_username()
+    (*random_from_array(&FAKE_USERNAMES)).to_string()
 }
 
 fn syslog_version() -> usize {