Merge pull request #477 from crocs-muni/fix/no-more-retcode

Get rid of RETURNCODE_OK. This is not C99.

13 files changed, 129 insertions, 186 deletions

diff --git a/src/sec_certs/constants.py b/src/sec_certs/constants.py
index 125c2265..ccc3887e 100644
--- a/src/sec_certs/constants.py
+++ b/src/sec_certs/constants.py
@@ -10,9 +10,6 @@ REF_EMBEDDING_METHOD = Literal["tf_idf", "transformer"]
 # This stupid thing should die in a fire...
 DUMMY_NONEXISTING_PATH = Path("/this/is/dummy/nonexisting/path")
 
-RESPONSE_OK = 200
-RETURNCODE_OK = "ok"
-RETURNCODE_NOK = "nok"
 REQUEST_TIMEOUT = 20
 
 INCREMENTAL_NVD_UPDATE_MAX_INTERVAL_DAYS: Final[int] = 120
diff --git a/src/sec_certs/dataset/auxiliary_dataset_handling.py b/src/sec_certs/dataset/auxiliary_dataset_handling.py
index 69d5e837..d89f6520 100644
--- a/src/sec_certs/dataset/auxiliary_dataset_handling.py
+++ b/src/sec_certs/dataset/auxiliary_dataset_handling.py
@@ -8,6 +8,8 @@ from collections.abc import Iterable
 from pathlib import Path
 from typing import Any, ClassVar
 
+import requests
+
 from sec_certs import constants
 from sec_certs.configuration import config
 from sec_certs.dataset.cc_scheme import CCSchemeDataset
@@ -138,7 +140,7 @@ class CPEMatchDictHandler(AuxiliaryDatasetHandler):
                         dset_path,
                         progress_bar_desc="Downloading CPE Match feed from web",
                     )
-                    == constants.RESPONSE_OK
+                    == requests.codes.ok
                 ):
                     raise RuntimeError(f"Could not download CPE Match feed from {config.cpe_match_latest_snapshot}.")
                 with gzip.open(str(dset_path)) as handle:
diff --git a/src/sec_certs/dataset/cpe.py b/src/sec_certs/dataset/cpe.py
index 56e6ac5d..3257d2a4 100644
--- a/src/sec_certs/dataset/cpe.py
+++ b/src/sec_certs/dataset/cpe.py
@@ -8,6 +8,7 @@ from pathlib import Path
 from typing import Any
 
 import pandas as pd
+import requests
 
 from sec_certs import constants
 from sec_certs.configuration import config
@@ -86,7 +87,7 @@ class CPEDataset(JSONPathDataset, ComplexSerializableType):
                     dset_path,
                     progress_bar_desc="Downloading CPEDataset from web",
                 )
-                == constants.RESPONSE_OK
+                == requests.codes.ok
             ):
                 raise RuntimeError(f"Could not download CPEDataset from {config.cpe_latest_snapshot}.")
             dset = cls.from_json(dset_path, is_compressed=True)
diff --git a/src/sec_certs/dataset/cve.py b/src/sec_certs/dataset/cve.py
index 6314040c..f76211ee 100644
--- a/src/sec_certs/dataset/cve.py
+++ b/src/sec_certs/dataset/cve.py
@@ -9,6 +9,7 @@ from typing import Any, ClassVar
 
 import numpy as np
 import pandas as pd
+import requests
 
 import sec_certs.configuration as config_module
 from sec_certs import constants
@@ -82,7 +83,7 @@ class CVEDataset(JSONPathDataset, ComplexSerializableType):
                     dset_path,
                     progress_bar_desc="Downloading CVEDataset from web",
                 )
-                == constants.RESPONSE_OK
+                == requests.codes.ok
             ):
                 raise RuntimeError(f"Could not download CVEDataset from {config_module.config.cve_latest_snapshot}.")
             dset = cls.from_json(dset_path, is_compressed=True)
diff --git a/src/sec_certs/dataset/dataset.py b/src/sec_certs/dataset/dataset.py
index 446cc5ff..c17109f3 100644
--- a/src/sec_certs/dataset/dataset.py
+++ b/src/sec_certs/dataset/dataset.py
@@ -12,6 +12,7 @@ from pathlib import Path
 from typing import Any, ClassVar, Generic, TypeVar, cast
 
 import pandas as pd
+import requests
 from pydantic import AnyHttpUrl
 
 from sec_certs import constants
@@ -192,7 +193,7 @@ class Dataset(Generic[CertSubType], ComplexSerializableType, ABC):
                     show_progress_bar=True,
                     progress_bar_desc=progress_bar_desc,
                 )
-                if res != constants.RESPONSE_OK:
+                if res != requests.codes.ok:
                     raise ValueError(f"Download failed: {res}")
                 with tarfile.open(dset_path, "r:gz") as tar:
                     tar.extractall(str(path))
diff --git a/src/sec_certs/dataset/fips_algorithm.py b/src/sec_certs/dataset/fips_algorithm.py
index 56163078..ee7d06a1 100644
--- a/src/sec_certs/dataset/fips_algorithm.py
+++ b/src/sec_certs/dataset/fips_algorithm.py
@@ -8,6 +8,7 @@ from pathlib import Path
 from tempfile import TemporaryDirectory
 
 import pandas as pd
+import requests
 from bs4 import BeautifulSoup
 
 from sec_certs import constants
@@ -64,9 +65,9 @@ class FIPSAlgorithmDataset(JSONPathDataset, ComplexSerializableType):
         ITEMS_PER_PAGE = "ipp=250"
 
         res = helpers.download_file(constants.FIPS_ALG_SEARCH_URL + "1&" + ITEMS_PER_PAGE, first_page_path)
-        if res != constants.RESPONSE_OK:
+        if res != requests.codes.ok:
             res = helpers.download_file(constants.FIPS_ALG_SEARCH_URL + "1&" + ITEMS_PER_PAGE, first_page_path)
-            if res != constants.RESPONSE_OK:
+            if res != requests.codes.ok:
                 logger.error(f"Could not build Algorithm dataset, got server response: {res}")
                 raise ValueError(f"Could not build Algorithm dataset, got server response: {res}")
 
@@ -76,13 +77,11 @@ class FIPSAlgorithmDataset(JSONPathDataset, ComplexSerializableType):
         paths = [output_dir / f"page{i}.html" for i in range(2, n_pages + 1)]
         responses = helpers.download_parallel(urls, paths, progress_bar_desc="Downloading FIPS Algorithm HTMLs")
 
-        failed_tuples = [
-            (url, path) for url, path, resp in zip(urls, paths, responses) if resp != constants.RESPONSE_OK
-        ]
+        failed_tuples = [(url, path) for url, path, resp in zip(urls, paths, responses) if resp != requests.codes.ok]
         if failed_tuples:
             failed_urls, failed_paths = zip(*failed_tuples)
             responses = helpers.download_parallel(failed_urls, failed_paths)
-            if any(x != constants.RESPONSE_OK for x in responses):
+            if any(x != requests.codes.ok for x in responses):
                 raise ValueError("Failed to download the algorithms HTML data, the dataset won't be constructed.")
 
         return paths
diff --git a/src/sec_certs/sample/cc.py b/src/sec_certs/sample/cc.py
index ca096a6c..e43333e9 100644
--- a/src/sec_certs/sample/cc.py
+++ b/src/sec_certs/sample/cc.py
@@ -7,15 +7,13 @@ from collections import Counter, defaultdict
 from dataclasses import dataclass, field
 from datetime import date, datetime
 from pathlib import Path
-from typing import Any, ClassVar
+from typing import Any, ClassVar, Literal
 from urllib.parse import unquote_plus, urlparse
 
 import numpy as np
 import requests
 from bs4 import Tag
 
-import sec_certs.utils.extract
-import sec_certs.utils.pdf
 from sec_certs import constants
 from sec_certs.cert_rules import SARS_IMPLIED_FROM_EAL, cc_rules, rules
 from sec_certs.configuration import config
@@ -28,7 +26,8 @@ from sec_certs.sample.sar import SAR
 from sec_certs.serialization.json import ComplexSerializableType
 from sec_certs.serialization.pandas import PandasSerializableType
 from sec_certs.utils import helpers, sanitization
-from sec_certs.utils.extract import normalize_match_string, scheme_frontpage_functions
+from sec_certs.utils.extract import extract_keywords, normalize_match_string, scheme_frontpage_functions
+from sec_certs.utils.pdf import convert_pdf_file, extract_pdf_metadata
 
 
 class CCCertificate(
@@ -662,7 +661,7 @@ class CCCertificate(
         :param Optional[Union[str, Path]] cert_pdf_dir: Directory where pdf certificates shall be stored
         :param Optional[Union[str, Path]] report_txt_dir: Directory where txt reports shall be stored
         :param Optional[Union[str, Path]] st_txt_dir: Directory where txt security targets shall be stored
-        :param Optional[Union[str, Path]] cert_txt_dir: Directory where txtcertificates shall be stored
+        :param Optional[Union[str, Path]] cert_txt_dir: Directory where txt certificates shall be stored
         """
         if report_pdf_dir:
             self.state.report.pdf_path = Path(report_pdf_dir) / (self.dgst + ".pdf")
@@ -678,6 +677,22 @@ class CCCertificate(
             self.state.cert.txt_path = Path(cert_txt_dir) / (self.dgst + ".txt")
 
     @staticmethod
+    def _download_pdf(cert: CCCertificate, doc_type: Literal["report", "st", "cert"]):
+        link = getattr(cert, f"{doc_type}_link")
+        doc_state = getattr(cert.state, doc_type)
+        exit_code = helpers.download_file(link, doc_state.pdf_path, proxy=config.cc_use_proxy) if link else "No link"
+
+        if exit_code != requests.codes.ok:
+            error_msg = f"failed to download {doc_type} from {link}, code: {exit_code}"
+            logger.error(f"Cert dgst: {cert.dgst} " + error_msg)
+            doc_state.download_ok = False
+        else:
+            doc_state.download_ok = True
+            doc_state.pdf_hash = helpers.get_sha256_filepath(doc_state.pdf_path)
+            setattr(cert.pdf_data, f"{doc_type}_filename", unquote_plus(str(urlparse(link).path).split("/")[-1]))
+        return cert
+
+    @staticmethod
     def download_pdf_report(cert: CCCertificate) -> CCCertificate:
         """
         Downloads pdf of certification report given the certificate. Staticmethod to allow for parallelization.
@@ -685,20 +700,7 @@ class CCCertificate(
         :param CCCertificate cert: cert to download the pdf report for
         :return CCCertificate: returns the modified certificate with updated state
         """
-        exit_code: str | int
-        if not cert.report_link:
-            exit_code = "No link"
-        else:
-            exit_code = helpers.download_file(cert.report_link, cert.state.report.pdf_path, proxy=config.cc_use_proxy)
-        if exit_code != requests.codes.ok:
-            error_msg = f"failed to download report from {cert.report_link}, code: {exit_code}"
-            logger.error(f"Cert dgst: {cert.dgst} " + error_msg)
-            cert.state.report.download_ok = False
-        else:
-            cert.state.report.download_ok = True
-            cert.state.report.pdf_hash = helpers.get_sha256_filepath(cert.state.report.pdf_path)
-            cert.pdf_data.report_filename = unquote_plus(str(urlparse(cert.report_link).path).split("/")[-1])
-        return cert
+        return CCCertificate._download_pdf(cert, "report")
 
     @staticmethod
     def download_pdf_st(cert: CCCertificate) -> CCCertificate:
@@ -708,21 +710,7 @@ class CCCertificate(
         :param CCCertificate cert: cert to download the pdf security target for
         :return CCCertificate: returns the modified certificate with updated state
         """
-        exit_code: str | int = (
-            helpers.download_file(cert.st_link, cert.state.st.pdf_path, proxy=config.cc_use_proxy)
-            if cert.st_link
-            else "No link"
-        )
-
-        if exit_code != requests.codes.ok:
-            error_msg = f"failed to download ST from {cert.st_link}, code: {exit_code}"
-            logger.error(f"Cert dgst: {cert.dgst} " + error_msg)
-            cert.state.st.download_ok = False
-        else:
-            cert.state.st.download_ok = True
-            cert.state.st.pdf_hash = helpers.get_sha256_filepath(cert.state.st.pdf_path)
-            cert.pdf_data.st_filename = unquote_plus(str(urlparse(cert.st_link).path).split("/")[-1])
-        return cert
+        return CCCertificate._download_pdf(cert, "st")
 
     @staticmethod
     def download_pdf_cert(cert: CCCertificate) -> CCCertificate:
@@ -732,20 +720,21 @@ class CCCertificate(
         :param CCCertificate cert: cert to download the pdf of
         :return CCCertificate: returns the modified certificate with updated state
         """
-        exit_code: str | int = (
-            helpers.download_file(cert.cert_link, cert.state.cert.pdf_path, proxy=config.cc_use_proxy)
-            if cert.cert_link
-            else "No link"
-        )
+        return CCCertificate._download_pdf(cert, "cert")
 
-        if exit_code != requests.codes.ok:
-            error_msg = f"failed to download certificate from {cert.cert_link}, code: {exit_code}"
+    @staticmethod
+    def _convert_pdf(cert: CCCertificate, doc_type: Literal["report", "st", "cert"]) -> CCCertificate:
+        doc_state = getattr(cert.state, doc_type)
+        ocr_done, ok_result = convert_pdf_file(doc_state.pdf_path, doc_state.txt_path)
+        # If OCR was done the result was garbage
+        doc_state.convert_garbage = ocr_done
+        # And put the whole result into convert_ok
+        doc_state.convert_ok = ok_result
+        if not ok_result:
+            error_msg = f"failed to convert {doc_type} pdf->txt"
             logger.error(f"Cert dgst: {cert.dgst} " + error_msg)
-            cert.state.cert.download_ok = False
         else:
-            cert.state.cert.download_ok = True
-            cert.state.cert.pdf_hash = helpers.get_sha256_filepath(cert.state.cert.pdf_path)
-            cert.pdf_data.cert_filename = unquote_plus(str(urlparse(cert.cert_link).path).split("/")[-1])
+            doc_state.txt_hash = helpers.get_sha256_filepath(doc_state.txt_path)
         return cert
 
     @staticmethod
@@ -756,19 +745,7 @@ class CCCertificate(
         :param CCCertificate cert: cert to convert the pdf report for
         :return CCCertificate: the modified certificate with updated state
         """
-        ocr_done, ok_result = sec_certs.utils.pdf.convert_pdf_file(
-            cert.state.report.pdf_path, cert.state.report.txt_path
-        )
-        # If OCR was done the result was garbage
-        cert.state.report.convert_garbage = ocr_done
-        # And put the whole result into convert_ok
-        cert.state.report.convert_ok = ok_result
-        if not ok_result:
-            error_msg = "failed to convert report pdf->txt"
-            logger.error(f"Cert dgst: {cert.dgst} " + error_msg)
-        else:
-            cert.state.report.txt_hash = helpers.get_sha256_filepath(cert.state.report.txt_path)
-        return cert
+        return CCCertificate._convert_pdf(cert, "report")
 
     @staticmethod
     def convert_st_pdf(cert: CCCertificate) -> CCCertificate:
@@ -778,17 +755,7 @@ class CCCertificate(
         :param CCCertificate cert: cert to convert the pdf security target for
         :return CCCertificate: the modified certificate with updated state
         """
-        ocr_done, ok_result = sec_certs.utils.pdf.convert_pdf_file(cert.state.st.pdf_path, cert.state.st.txt_path)
-        # If OCR was done the result was garbage
-        cert.state.st.convert_garbage = ocr_done
-        # And put the whole result into convert_ok
-        cert.state.st.convert_ok = ok_result
-        if not ok_result:
-            error_msg = "failed to convert security target pdf->txt"
-            logger.error(f"Cert dgst: {cert.dgst} " + error_msg)
-        else:
-            cert.state.st.txt_hash = helpers.get_sha256_filepath(cert.state.st.txt_path)
-        return cert
+        return CCCertificate._convert_pdf(cert, "st")
 
     @staticmethod
     def convert_cert_pdf(cert: CCCertificate) -> CCCertificate:
@@ -798,16 +765,17 @@ class CCCertificate(
         :param CCCertificate cert: cert to convert the certificate for
         :return CCCertificate: the modified certificate with updated state
         """
-        ocr_done, ok_result = sec_certs.utils.pdf.convert_pdf_file(cert.state.cert.pdf_path, cert.state.cert.txt_path)
-        # If OCR was done the result was garbage
-        cert.state.cert.convert_garbage = ocr_done
-        # And put the whole result into convert_ok
-        cert.state.cert.convert_ok = ok_result
-        if not ok_result:
-            error_msg = "failed to convert security target pdf->txt"
-            logger.error(f"Cert dgst: {cert.dgst} " + error_msg)
-        else:
-            cert.state.cert.txt_hash = helpers.get_sha256_filepath(cert.state.cert.txt_path)
+        return CCCertificate._convert_pdf(cert, "cert")
+
+    @staticmethod
+    def _extract_pdf_metadata(cert: CCCertificate, doc_type: Literal["report", "st", "cert"]) -> CCCertificate:
+        doc_state = getattr(cert.state, doc_type)
+        try:
+            metadata = extract_pdf_metadata(doc_state.pdf_path)
+            setattr(cert.pdf_data, f"{doc_type}_metadata", metadata)
+            doc_state.extract_ok = True
+        except ValueError:
+            doc_state.extract_ok = False
         return cert
 
     @staticmethod
@@ -818,12 +786,7 @@ class CCCertificate(
         :param CCCertificate cert: cert to extract the metadata for.
         :return CCCertificate: the modified certificate with updated state
         """
-        response, cert.pdf_data.report_metadata = sec_certs.utils.pdf.extract_pdf_metadata(cert.state.report.pdf_path)
-        if response != constants.RETURNCODE_OK:
-            cert.state.report.extract_ok = False
-        else:
-            cert.state.report.extract_ok = True
-        return cert
+        return CCCertificate._extract_pdf_metadata(cert, "report")
 
     @staticmethod
     def extract_st_pdf_metadata(cert: CCCertificate) -> CCCertificate:
@@ -833,12 +796,7 @@ class CCCertificate(
         :param CCCertificate cert: cert to extract the metadata for.
         :return CCCertificate: the modified certificate with updated state
         """
-        response, cert.pdf_data.st_metadata = sec_certs.utils.pdf.extract_pdf_metadata(cert.state.st.pdf_path)
-        if response != constants.RETURNCODE_OK:
-            cert.state.st.extract_ok = False
-        else:
-            cert.state.st.extract_ok = True
-        return cert
+        return CCCertificate._extract_pdf_metadata(cert, "st")
 
     @staticmethod
     def extract_cert_pdf_metadata(cert: CCCertificate) -> CCCertificate:
@@ -848,12 +806,7 @@ class CCCertificate(
         :param CCCertificate cert: cert to extract the metadata for.
         :return CCCertificate: the modified certificate with updated state
         """
-        response, cert.pdf_data.cert_metadata = sec_certs.utils.pdf.extract_pdf_metadata(cert.state.cert.pdf_path)
-        if response != constants.RETURNCODE_OK:
-            cert.state.cert.extract_ok = False
-        else:
-            cert.state.cert.extract_ok = True
-        return cert
+        return CCCertificate._extract_pdf_metadata(cert, "cert")
 
     @staticmethod
     def extract_report_pdf_frontpage(cert: CCCertificate) -> CCCertificate:
@@ -867,12 +820,26 @@ class CCCertificate(
 
         if cert.scheme in scheme_frontpage_functions:
             header_func = scheme_frontpage_functions[cert.scheme]
-            response, cert.pdf_data.report_frontpage[cert.scheme] = header_func(cert.state.report.txt_path)
-            if response != constants.RETURNCODE_OK:
+            try:
+                cert.pdf_data.report_frontpage[cert.scheme] = header_func(cert.state.report.txt_path)
+            except ValueError:
                 cert.state.report.extract_ok = False
         return cert
 
     @staticmethod
+    def _extract_pdf_keywords(cert: CCCertificate, doc_type: Literal["report", "st", "cert"]) -> CCCertificate:
+        doc_state = getattr(cert.state, doc_type)
+        try:
+            keywords = extract_keywords(doc_state.txt_path, cc_rules)
+            if keywords is None:
+                doc_state.extract_ok = False
+            else:
+                setattr(cert.pdf_data, f"{doc_type}_keywords", keywords)
+        except ValueError:
+            doc_state.extract_ok = False
+        return cert
+
+    @staticmethod
     def extract_report_pdf_keywords(cert: CCCertificate) -> CCCertificate:
         """
         Matches regular expressions in txt obtained from certification report and extracts the matches into attribute.
@@ -881,12 +848,7 @@ class CCCertificate(
         :param CCCertificate cert: certificate to extract the keywords for.
         :return CCCertificate: the modified certificate with extracted keywords.
         """
-        report_keywords = sec_certs.utils.extract.extract_keywords(cert.state.report.txt_path, cc_rules)
-        if report_keywords is None:
-            cert.state.report.extract_ok = False
-        else:
-            cert.pdf_data.report_keywords = report_keywords
-        return cert
+        return CCCertificate._extract_pdf_keywords(cert, "report")
 
     @staticmethod
     def extract_st_pdf_keywords(cert: CCCertificate) -> CCCertificate:
@@ -897,12 +859,7 @@ class CCCertificate(
         :param CCCertificate cert: certificate to extract the keywords for.
         :return CCCertificate: the modified certificate with extracted keywords.
         """
-        st_keywords = sec_certs.utils.extract.extract_keywords(cert.state.st.txt_path, cc_rules)
-        if st_keywords is None:
-            cert.state.st.extract_ok = False
-        else:
-            cert.pdf_data.st_keywords = st_keywords
-        return cert
+        return CCCertificate._extract_pdf_keywords(cert, "st")
 
     @staticmethod
     def extract_cert_pdf_keywords(cert: CCCertificate) -> CCCertificate:
@@ -913,12 +870,7 @@ class CCCertificate(
         :param CCCertificate cert: certificate to extract the keywords for.
         :return CCCertificate: the modified certificate with extracted keywords.
         """
-        cert_keywords = sec_certs.utils.extract.extract_keywords(cert.state.cert.txt_path, cc_rules)
-        if cert_keywords is None:
-            cert.state.cert.extract_ok = False
-        else:
-            cert.pdf_data.cert_keywords = cert_keywords
-        return cert
+        return CCCertificate._extract_pdf_keywords(cert, "cert")
 
     def compute_heuristics_cert_versions(self, cert_ids: dict[str, CertificateId | None]) -> None:  # noqa: C901
         """
diff --git a/src/sec_certs/sample/fips.py b/src/sec_certs/sample/fips.py
index ce2e6907..7480991c 100644
--- a/src/sec_certs/sample/fips.py
+++ b/src/sec_certs/sample/fips.py
@@ -23,8 +23,9 @@ from sec_certs.sample.certificate import PdfData as BasePdfData
 from sec_certs.sample.cpe import CPE
 from sec_certs.serialization.json import ComplexSerializableType
 from sec_certs.serialization.pandas import PandasSerializableType
-from sec_certs.utils import extract, helpers, pdf, tables
+from sec_certs.utils import extract, helpers, tables
 from sec_certs.utils.helpers import fips_dgst
+from sec_certs.utils.pdf import convert_pdf_file, extract_pdf_metadata, repair_pdf
 
 
 class FIPSHTMLParser:
@@ -590,7 +591,7 @@ class FIPSCertificate(
         """
         Converts policy pdf -> txt
         """
-        ocr_done, ok_result = pdf.convert_pdf_file(cert.state.policy_pdf_path, cert.state.policy_txt_path)
+        ocr_done, ok_result = convert_pdf_file(cert.state.policy_pdf_path, cert.state.policy_txt_path)
 
         # If OCR was done and the result was garbage
         cert.state.policy_convert_garbage = ocr_done
@@ -610,12 +611,9 @@ class FIPSCertificate(
         """
         Extract the PDF metadata from the security policy.
         """
-        _, metadata = pdf.extract_pdf_metadata(cert.state.policy_pdf_path)
-
-        if metadata:
-            cert.pdf_data.policy_metadata = metadata
-        else:
-            cert.pdf_data.policy_metadata = {}
+        try:
+            cert.pdf_data.policy_metadata = extract_pdf_metadata(cert.state.policy_pdf_path)
+        except ValueError:
             cert.state.policy_extract_ok = False
         return cert
 
@@ -640,7 +638,7 @@ class FIPSCertificate(
         from tabula import read_pdf
 
         if table_rich_page_numbers := tables.find_pages_with_tables(cert.state.policy_txt_path):
-            pdf.repair_pdf(cert.state.policy_pdf_path)
+            repair_pdf(cert.state.policy_pdf_path)
             try:
                 tabular_data = read_pdf(cert.state.policy_pdf_path, pages=list(table_rich_page_numbers), silent=True)
                 cert.heuristics.algorithms |= set(
diff --git a/src/sec_certs/sample/protection_profile.py b/src/sec_certs/sample/protection_profile.py
index 35eab2dc..87565c40 100644
--- a/src/sec_certs/sample/protection_profile.py
+++ b/src/sec_certs/sample/protection_profile.py
@@ -9,8 +9,6 @@ from urllib.parse import unquote_plus, urlparse
 import requests
 from bs4 import Tag
 
-import sec_certs.utils.extract
-import sec_certs.utils.pdf
 from sec_certs import constants
 from sec_certs.cert_rules import cc_rules
 from sec_certs.configuration import config
@@ -20,6 +18,8 @@ from sec_certs.sample.certificate import PdfData as BasePdfData
 from sec_certs.sample.document_state import DocumentState
 from sec_certs.serialization.json import ComplexSerializableType
 from sec_certs.utils import cc_html_parsing, helpers, sanitization
+from sec_certs.utils.extract import extract_keywords
+from sec_certs.utils.pdf import convert_pdf_file, extract_pdf_metadata
 
 
 class ProtectionProfile(
@@ -259,7 +259,7 @@ class ProtectionProfile(
         """
         Downloads pdf of certification report for the given protection profile.
         """
-        exit_code: str | int
+        exit_code: str | int | None
         if not cert.web_data.report_link:
             exit_code = "No link"
         else:
@@ -281,7 +281,7 @@ class ProtectionProfile(
         """
         Downloads actual pdf of the given protection profile.
         """
-        exit_code: str | int
+        exit_code: str | int | None
         if not cert.web_data.pp_link:
             exit_code = "No link"
         else:
@@ -301,9 +301,7 @@ class ProtectionProfile(
         """
         Converts certification reports from pdf to txt.
         """
-        ocr_done, ok_result = sec_certs.utils.pdf.convert_pdf_file(
-            cert.state.report.pdf_path, cert.state.report.txt_path
-        )
+        ocr_done, ok_result = convert_pdf_file(cert.state.report.pdf_path, cert.state.report.txt_path)
         cert.state.report.convert_garbage = ocr_done
         cert.state.report.convert_ok = ok_result
         if not ok_result:
@@ -317,7 +315,7 @@ class ProtectionProfile(
         """
         Converts the actual protection profile from pdf to txt.
         """
-        ocr_done, ok_result = sec_certs.utils.pdf.convert_pdf_file(cert.state.pp.pdf_path, cert.state.pp.txt_path)
+        ocr_done, ok_result = convert_pdf_file(cert.state.pp.pdf_path, cert.state.pp.txt_path)
         cert.state.pp.convert_garbage = ocr_done
         cert.state.pp.convert_ok = ok_result
         if not ok_result:
@@ -331,8 +329,11 @@ class ProtectionProfile(
         """
         Extracts various pdf metadata from the certification report.
         """
-        response, cert.pdf_data.report_metadata = sec_certs.utils.pdf.extract_pdf_metadata(cert.state.report.pdf_path)
-        cert.state.report.extract_ok = response == constants.RETURNCODE_OK
+        try:
+            cert.pdf_data.report_metadata = extract_pdf_metadata(cert.state.report.pdf_path)
+            cert.state.report.extract_ok = True
+        except ValueError:
+            cert.state.report.extract_ok = False
         return cert
 
     @staticmethod
@@ -340,8 +341,12 @@ class ProtectionProfile(
         """
         Extracts various pdf metadata from the actual protection profile.
         """
-        response, cert.pdf_data.pp_metadata = sec_certs.utils.pdf.extract_pdf_metadata(cert.state.pp.pdf_path)
-        cert.state.pp.extract_ok = response == constants.RETURNCODE_OK
+        try:
+            cert.pdf_data.pp_metadata = extract_pdf_metadata(cert.state.pp.pdf_path)
+            cert.state.pp.extract_ok = True
+        except ValueError:
+            cert.state.pp.extract_ok = False
+
         return cert
 
     @staticmethod
@@ -349,7 +354,7 @@ class ProtectionProfile(
         """
         Extracts keywords using regexes from the certification report.
         """
-        report_keywords = sec_certs.utils.extract.extract_keywords(cert.state.report.txt_path, cc_rules)
+        report_keywords = extract_keywords(cert.state.report.txt_path, cc_rules)
         if report_keywords is None:
             cert.state.report.extract_ok = False
         else:
@@ -361,7 +366,7 @@ class ProtectionProfile(
         """
         Extracts keywords using regexes from the actual protection profile.
         """
-        pp_keywords = sec_certs.utils.extract.extract_keywords(cert.state.pp.txt_path, cc_rules)
+        pp_keywords = extract_keywords(cert.state.pp.txt_path, cc_rules)
         if pp_keywords is None:
             cert.state.pp.extract_ok = False
         else:
diff --git a/src/sec_certs/utils/extract.py b/src/sec_certs/utils/extract.py
index 6af7f4cc..35361e94 100644
--- a/src/sec_certs/utils/extract.py
+++ b/src/sec_certs/utils/extract.py
@@ -267,19 +267,9 @@ def search_only_headers_anssi(filepath: Path):  # noqa: C901
         relative_filepath = "/".join(str(filepath).split("/")[-4:])
         error_msg = f"Failed to parse ANSSI frontpage headers from {relative_filepath}; {e}"
         logger.error(error_msg)
-        return error_msg, None
+        raise ValueError(error_msg) from e
 
-    # if True:
-    #     print('# hits for rule')
-    #     sorted_rules = sorted(num_rules_hits.items(),
-    #                           key=operator.itemgetter(1), reverse=True)
-    #     used_rules = []
-    #     for rule in sorted_rules:
-    #         print('{:4d} : {}'.format(rule[1], rule[0]))
-    #         if rule[1] > 0:
-    #             used_rules.append(rule[0])
-
-    return constants.RETURNCODE_OK, items_found
+    return items_found
 
 
 def search_only_headers_bsi(filepath: Path):  # noqa: C901
@@ -376,9 +366,9 @@ def search_only_headers_bsi(filepath: Path):  # noqa: C901
         relative_filepath = "/".join(str(filepath).split("/")[-4:])
         error_msg = f"Failed to parse BSI headers from frontpage: {relative_filepath}; {e}"
         logger.error(error_msg)
-        return error_msg, None
+        raise ValueError(error_msg) from e
 
-    return constants.RETURNCODE_OK, items_found
+    return items_found
 
 
 def search_only_headers_nscib(filepath: Path):  # noqa: C901
@@ -456,9 +446,9 @@ def search_only_headers_nscib(filepath: Path):  # noqa: C901
     except Exception as e:
         error_msg = f"Failed to parse NSCIB headers from frontpage: {filepath}; {e}"
         logger.error(error_msg)
-        return error_msg, None
+        raise ValueError(error_msg) from e
 
-    return constants.RETURNCODE_OK, items_found
+    return items_found
 
 
 def search_only_headers_niap(filepath: Path):
@@ -507,9 +497,9 @@ def search_only_headers_niap(filepath: Path):
     except Exception as e:
         error_msg = f"Failed to parse NIAP headers from frontpage: {filepath}; {e}"
         logger.error(error_msg)
-        return error_msg, None
+        raise ValueError(error_msg) from e
 
-    return constants.RETURNCODE_OK, items_found
+    return items_found
 
 
 def search_only_headers_canada(filepath: Path):  # noqa: C901
@@ -580,9 +570,9 @@ def search_only_headers_canada(filepath: Path):  # noqa: C901
     except Exception as e:
         error_msg = f"Failed to parse Canada headers from frontpage: {filepath}; {e}"
         logger.error(error_msg)
-        return error_msg, None
+        raise ValueError(error_msg) from e
 
-    return constants.RETURNCODE_OK, items_found
+    return items_found
 
 
 def flatten_matches(dct: dict) -> dict:
diff --git a/src/sec_certs/utils/helpers.py b/src/sec_certs/utils/helpers.py
index 63de6fd9..4f0e4136 100644
--- a/src/sec_certs/utils/helpers.py
+++ b/src/sec_certs/utils/helpers.py
@@ -102,8 +102,7 @@ def download_file(  # noqa: C901
     show_progress_bar: bool = False,
     progress_bar_desc: str | None = None,
     proxy: bool = False,
-) -> str | int:
-    """Download a file from a URL to a local path."""
+) -> int | None:
     try:
         proxied = False
         if proxy:
@@ -142,13 +141,12 @@ def download_file(  # noqa: C901
                     if show_progress_bar:
                         pbar.update(len(data))
 
-            return r.status_code
+        return r.status_code
     except requests.exceptions.Timeout:
         return requests.codes.timeout
     except Exception as e:
         logger.error(f"Failed to download from {url}; {e}")
-        return constants.RETURNCODE_NOK
-    return constants.RETURNCODE_NOK
+        return None
 
 
 def download_parallel(
diff --git a/src/sec_certs/utils/nvd_dataset_builder.py b/src/sec_certs/utils/nvd_dataset_builder.py
index 4e7162eb..bffde677 100644
--- a/src/sec_certs/utils/nvd_dataset_builder.py
+++ b/src/sec_certs/utils/nvd_dataset_builder.py
@@ -192,7 +192,7 @@ class NvdDatasetBuilder(Generic[DatasetType], ABC):
         if response.status_code == 404:
             # This is likely due to no CPEs to update, incremental update very soon.
             return 0
-        if response.status_code != constants.RESPONSE_OK:
+        if response.status_code != requests.codes.ok:
             if fresh:
                 logger.warning(
                     f"Error when attempting to fetch number of pages to get from NVD API {self._ENDPOINT} endpoint, sleeping 6 seconds and repeating."
@@ -227,9 +227,9 @@ class NvdDatasetBuilder(Generic[DatasetType], ABC):
         """
         Will fetch successfull responses into self._ok_responses and prune self.requests_to_process accordingly
         """
-        response_is_nok = np.array([x.status_code != constants.RESPONSE_OK for x in responses])
+        response_is_nok = np.array([x.status_code != requests.codes.ok for x in responses])
         nok_indices = np.where(response_is_nok == True)[0]  # noqa E712, doesn't work with `is True`
-        currently_ok = [x for x in responses if x.status_code == constants.RESPONSE_OK]
+        currently_ok = [x for x in responses if x.status_code == requests.codes.ok]
 
         logger.info(
             f"Attempt {self.max_attempts - self._attempts_left}/{self.max_attempts}: Successfully processed {len(currently_ok)}/{len(self._requests_to_process)} requests."
diff --git a/src/sec_certs/utils/pdf.py b/src/sec_certs/utils/pdf.py
index 3195e67e..39046717 100644
--- a/src/sec_certs/utils/pdf.py
+++ b/src/sec_certs/utils/pdf.py
@@ -13,7 +13,6 @@ import pikepdf
 import pytesseract
 from PIL import Image
 
-from sec_certs import constants
 from sec_certs.constants import (
     GARBAGE_ALPHA_CHARS_THRESHOLD,
     GARBAGE_AVG_LLEN_THRESHOLD,
@@ -151,7 +150,7 @@ def parse_pdf_date(dateval: bytes | None) -> datetime | None:
         return None
 
 
-def extract_pdf_metadata(filepath: Path) -> tuple[str, dict[str, Any] | None]:  # noqa: C901
+def extract_pdf_metadata(filepath: Path) -> dict[str, Any]:  # noqa: C901
     """
     Extract PDF metadata, such as the number of pages, author, title, etc.
 
@@ -237,9 +236,9 @@ def extract_pdf_metadata(filepath: Path) -> tuple[str, dict[str, Any] | None]:
         relative_filepath = "/".join(str(filepath).split("/")[-4:])
         error_msg = f"Failed to read metadata of {relative_filepath}, error: {e}"
         logger.error(error_msg)
-        return error_msg, None
+        raise ValueError(error_msg)
 
-    return constants.RETURNCODE_OK, metadata
+    return metadata
 
 
 def text_is_garbage(text: str) -> bool:
@@ -274,7 +273,7 @@ def text_is_garbage(text: str) -> bool:
     # If the average length of a line is small, this is garbage.
     if avg_line_len < GARBAGE_AVG_LLEN_THRESHOLD:
         return True
-    # If there a small amount of lines that have more than one character at every second character, this is garbage.
+    # If there is a small amount of lines that have more than one character at every second character, this is garbage.
     # This detects the ANSSI spacing issues.
     if every_second < GARBAGE_EVERY_SECOND_CHAR_THRESHOLD:
         return True