load("@databuild//databuild:rules.bzl", "databuild_graph", "databuild_job")
load("@pypi//:requirements.bzl", "requirement")
load("@rules_python//python:pip.bzl", "compile_pip_requirements")
load("//:py_repl.bzl", "py_repl")

compile_pip_requirements(
    name = "py_requirements",
    src = "requirements.in",
    requirements_txt = "requirements_lock.txt",
)

platform(
    name = "linux_arm",
    constraint_values = [
        "@platforms//os:linux",
        "@platforms//cpu:arm64",
    ],
)

platform(
    name = "linux_x86",
    constraint_values = [
        "@platforms//os:linux",
        "@platforms//cpu:x86_64",
    ],
)

# Podcast Reviews Graph
databuild_graph(
    name = "podcast_reviews_graph",
    jobs = [
        ":extract_reviews_job",
        ":extract_podcasts_job",
        ":categorize_reviews_job",
        ":phrase_modeling_job",
        ":phrase_stats_job",
        ":daily_summary_job",
    ],
    lookup = ":job_lookup",
    visibility = ["//visibility:public"],
)

py_binary(
    name = "job_lookup",
    srcs = ["job_lookup.py"],
    main = "job_lookup.py",
)

# Extract Reviews Job
databuild_job(
    name = "extract_reviews_job",
    binary = ":extract_reviews_binary",
    visibility = ["//visibility:public"],
)

py_binary(
    name = "extract_reviews_binary",
    srcs = [
        "duckdb_utils.py",
        "extract_reviews_job.py",
    ],
    main = "extract_reviews_job.py",
    deps = [
        requirement("duckdb"),
        requirement("pydantic"),
        requirement("pandas"),
        requirement("pyarrow"),
    ],
)

# Extract Podcasts Job
databuild_job(
    name = "extract_podcasts_job",
    binary = ":extract_podcasts_binary",
    visibility = ["//visibility:public"],
)

py_binary(
    name = "extract_podcasts_binary",
    srcs = [
        "duckdb_utils.py",
        "extract_podcasts_job.py",
    ],
    main = "extract_podcasts_job.py",
    deps = [
        requirement("duckdb"),
        requirement("pydantic"),
        requirement("pandas"),
        requirement("pyarrow"),
    ],
)

# Categorize Reviews Job
databuild_job(
    name = "categorize_reviews_job",
    binary = ":categorize_reviews_binary",
    visibility = ["//visibility:public"],
)

py_binary(
    name = "categorize_reviews_binary",
    srcs = [
        "categorize_reviews_job.py",
        "duckdb_utils.py",
    ],
    main = "categorize_reviews_job.py",
    deps = [
        requirement("duckdb"),
        requirement("pydantic"),
        requirement("pandas"),
        requirement("pyarrow"),
    ],
)

# Phrase Modeling Job
databuild_job(
    name = "phrase_modeling_job",
    binary = ":phrase_modeling_binary",
    visibility = ["//visibility:public"],
)

py_binary(
    name = "phrase_modeling_binary",
    srcs = [
        "duckdb_utils.py",
        "phrase_modeling_job.py",
    ],
    main = "phrase_modeling_job.py",
    deps = [
        requirement("duckdb"),
        requirement("pydantic"),
        requirement("pandas"),
        requirement("pyarrow"),
    ],
)

# Phrase Stats Job
databuild_job(
    name = "phrase_stats_job",
    binary = ":phrase_stats_binary",
    visibility = ["//visibility:public"],
)

py_binary(
    name = "phrase_stats_binary",
    srcs = [
        "duckdb_utils.py",
        "phrase_stats_job.py",
    ],
    main = "phrase_stats_job.py",
    deps = [
        requirement("duckdb"),
        requirement("pydantic"),
        requirement("pandas"),
        requirement("pyarrow"),
    ],
)

# Daily Summary Job
databuild_job(
    name = "daily_summary_job",
    binary = ":daily_summary_binary",
    visibility = ["//visibility:public"],
)

py_binary(
    name = "daily_summary_binary",
    srcs = [
        "daily_summary_job.py",
        "duckdb_utils.py",
    ],
    main = "daily_summary_job.py",
    deps = [
        requirement("duckdb"),
        requirement("pydantic"),
        requirement("pandas"),
        requirement("pyarrow"),
    ],
)

# Test target
py_binary(
    name = "test_jobs",
    srcs = [
        "categorize_reviews_job.py",
        "daily_summary_job.py",
        "duckdb_utils.py",
        "extract_podcasts_job.py",
        "extract_reviews_job.py",
        "job_lookup.py",
        "phrase_modeling_job.py",
        "phrase_stats_job.py",
        "test_jobs.py",
    ],
    main = "test_jobs.py",
    deps = [
        requirement("duckdb"),
        requirement("pydantic"),
        requirement("pandas"),
        requirement("pyarrow"),
    ],
)

py_repl(
    name = "repl",
    deps = [
        requirement("duckdb"),
        requirement("pydantic"),
    ],
)