public void TestGetDocumentMetaInfo_on_doc1()
{
string pdf_filename = MiscTestHelpers.GetNormalizedPathToAnyTestDataTestFile(@"fixtures/1.Doc-Many.Metadata.Formats/0001-LDA-paper/2004.04.PNAS.ef997ae1b01762b57b75d8c22fb8cec87406.pdf");
ASSERT.FileExists(pdf_filename);
PDFDocumentMuPDFMetaInfo info = MuPDFRenderer.GetDocumentMetaInfo(pdf_filename, null, ProcessPriorityClass.Normal);
ASSERT.AreEqual <int>(8, info.PageCount);
ASSERT.AreEqual <bool>(false, info.DocumentIsCorrupted);
ASSERT.IsLessOrEqual(10000, info.raw_multipurp_text.Length);
TestJSONoutputIsCorrectForPDFdoc1(info.raw_decoded_json);
object json_doc = JsonConvert.DeserializeObject(info.raw_multipurp_text);
string json_text = JsonConvert.SerializeObject(json_doc, Formatting.Indented).Replace("\r\n", "\n");
// Perform comparison via ApprovalTests->BeyondCompare (that's what I use for *decades* now)
//ApprovalTests.Approvals.VerifyJson(json_out); --> becomes the code below:
ApprovalTests.Approvals.Verify(
new QiqqaApprover(json_text, pdf_filename),
ApprovalTests.Approvals.GetReporter()
);
info.ClearRawContent();
ASSERT.IsNull(info.raw_multipurp_text);
ASSERT.IsNull(info.raw_decoded_json);
}
public void Basic_Import_Test(string ris_filepath)
{
string path = GetNormalizedPathToRISTestFile(ris_filepath);
ASSERT.FileExists(path);
string ris_text = GetTestFileContent(path);
Result rv = new Result();
rv.lines_set = SplitMultipleRISLines(ris_text);
foreach (List <string> lines in rv.lines_set)
{
RISRecord record = MapRISLinesToDictionary(lines);
rv.records.Add(record);
rv.bibtex_items.Add(record.ToBibTeX());
}
// Serialize the result to JSON for easier comparison via ApprovalTests->BeyondCompare (that's what I use for *decades* now)
string json_out = JsonConvert.SerializeObject(rv, Newtonsoft.Json.Formatting.Indented).Replace("\r\n", "\n");
//ApprovalTests.Approvals.VerifyJson(json_out); --> becomes the code below:
ApprovalTests.Approvals.Verify(
new QiqqaApprover(json_out, ris_filepath),
ApprovalTests.Approvals.GetReporter()
);
}
public void Test_SPEED(string filepath)
{
string path = GetNormalizedPathToAnyTestDataTestFile(filepath);
ASSERT.FileExists(path);
string data_in = GetTestFileContent(path);
string s1 = data_in;
string s2 = BibTexCharacterMap.ASCIIToBibTex(s1);
string s3 = BibTexCharacterMap.BibTexToASCII(s2);
const int NUM = 1000000;
const int CHUNK = 10000;
Stopwatch start = Stopwatch.StartNew();
int i;
for (i = 0; i < NUM; ++i)
{
if (i % CHUNK == CHUNK - 1)
{
// don't run for more than 2 seconds
if (start.ElapsedMilliseconds >= 2000)
{
break;
}
}
s2 = BibTexCharacterMap.ASCIIToBibTex(s1);
}
double time_a2b = i * 1.0E-3 * s1.Length / start.ElapsedMilliseconds;
Logging.Info("ASCIIToBibTex can do {0:0.000}M operations per second per character", time_a2b);
start = Stopwatch.StartNew();
for (i = 0; i < NUM; ++i)
{
if (i % CHUNK == CHUNK - 1)
{
// don't run for more than 2 seconds
if (start.ElapsedMilliseconds >= 2000)
{
break;
}
}
s3 = BibTexCharacterMap.BibTexToASCII(s2);
}
double time_b2a = i * 1.0E-3 * s1.Length / start.ElapsedMilliseconds;
Logging.Info("BibTexToASCII can do {0:0.000}M operations per second per character", time_b2a);
// dummy
BibTexCharacterMap.ASCIIToBibTex(s3);
}
public void TestMuPDF_multipurp_JSON_formatted_snippet1_parses_okay()
{
string json_filename = MiscTestHelpers.GetNormalizedPathToAnyTestDataTestFile(@"fixtures/mutool/multipurp/json-snippets/pdf-info1-formatted.json");
ASSERT.FileExists(json_filename);
string json = File.ReadAllText(json_filename);
ASSERT.IsNotNull(json);
List <MultiPurpDocumentInfoObject> infos_list = JsonConvert.DeserializeObject <List <MultiPurpDocumentInfoObject> >(json);
TestJSONoutputIsCorrectForPDFdoc1(infos_list);
}
public void Deserialize_v80_ClassicalQiqqaRecord(string input_path)
{
ASSERT.IsTrue(true);
string path = GetNormalizedPathToSerializationTestFile(input_path);
ASSERT.FileExists(path);
string input = GetTestFileContent(path);
PDFDocument record = JsonConvert.DeserializeObject <PDFDocument>(input);
ASSERT.IsTrue(true);
}
public void Test_Conversion_To_BibTeX_Text(string filepath)
{
string path = GetNormalizedPathToAnyTestDataTestFile(filepath);
ASSERT.FileExists(path);
string data_in = GetTestFileContent(path);
string s1 = data_in;
string s2 = BibTexCharacterMap.ASCIIToBibTex(s1);
ApprovalTests.Approvals.Verify(
new QiqqaApprover(s2, filepath),
ApprovalTests.Approvals.GetReporter()
);
}
public void Test_PDF_metadata_extraction_via_multipurp_chunk0070_qpdf(string filepath)
{
string pdf_filename = MiscTestHelpers.GetNormalizedPathToAnyTestDataTestFile($"fixtures/PDF/{ filepath.Replace("./", "") }");
ASSERT.FileExists(pdf_filename);
PDFDocumentMuPDFMetaInfo info = MuPDFRenderer.GetDocumentMetaInfo(pdf_filename, null, ProcessPriorityClass.Normal);
string json_text = ProduceJSONtext4Comparison(info);
// Perform comparison via ApprovalTests->BeyondCompare (that's what I use for *decades* now)
//ApprovalTests.Approvals.VerifyJson(json_out); --> becomes the code below:
ApprovalTests.Approvals.Verify(
new QiqqaApprover(json_text, pdf_filename),
ApprovalTests.Approvals.GetReporter()
);
}
public void Basic_Test(string sample_filepath)
{
string path = GetNormalizedPathToAnyTestDataTestFile(sample_filepath);
ASSERT.FileExists(path);
string sample_text = GetTestFileContent(path);
// extract URL from sample file:
string url = null;
string docHtml = null;
Match match = Regex.Match(sample_text, @"<!--(.*?)-->(.*)", RegexOptions.Singleline); // counter-intuitive flag: https://stackoverflow.com/questions/159118/how-do-i-match-any-character-across-multiple-lines-in-a-regular-expression
if (Match.Empty != match)
{
url = match.Groups[1].Value.Trim();
docHtml = match.Groups[2].Value;
}
List <GoogleScholarScrapePaper> gssps = new List <GoogleScholarScrapePaper>();
HtmlDocument doc = new HtmlDocument();
doc.LoadHtml(docHtml);
//doc.Load(ms, System.Text.Encoding.UTF8, detectEncodingFromByteOrderMarks: false);
ScrapeDoc(doc, url, ref gssps);
ASSERT.IsGreaterOrEqual(gssps.Count, 1);
// Serialize the result to JSON for easier comparison via ApprovalTests->BeyondCompare (that's what I use for *decades* now)
string json_out = JsonConvert.SerializeObject(gssps, Newtonsoft.Json.Formatting.Indented).Replace("\r\n", "\n");
//ApprovalTests.Approvals.VerifyJson(json_out); --> becomes the code below:
ApprovalTests.Approvals.Verify(
new QiqqaApprover(json_out, sample_filepath),
ApprovalTests.Approvals.GetReporter()
);
}
public void GetFirstWord_Test(string data_filepath)
{
string path = GetNormalizedPathToAnyTestDataTestFile(data_filepath);
ASSERT.FileExists(path);
string data_text = GetTestFileContent(path);
Result rv = new Result();
rv.input = data_text;
rv.result = StringTools.GetFirstWord(data_text);
// Serialize the result to JSON for easier comparison via ApprovalTests->BeyondCompare (that's what I use for *decades* now)
string json_out = JsonConvert.SerializeObject(rv, Newtonsoft.Json.Formatting.Indented).Replace("\r\n", "\n");
//ApprovalTests.Approvals.VerifyJson(json_out); --> becomes the code below:
ApprovalTests.Approvals.Verify(
new QiqqaApprover(json_out, data_filepath),
ApprovalTests.Approvals.GetReporter()
);
}
public void Basic_Import_Test(string pubmed_filepath)
{
// See http://www.nlm.nih.gov/bsd/licensee/elements_descriptions.html for the low-down
string path = GetNormalizedPathToPubMedXMLTestFile(pubmed_filepath);
ASSERT.FileExists(path);
string pubmed_xml = GetTestFileContent(path);
Result rv = new Result();
rv.success = PubMedXMLToBibTex.TryConvert(pubmed_xml, out rv.bibtex, out rv.messages);
// Serialize the result to JSON for easier comparison via ApprovalTests->BeyondCompare (that's what I use for *decades* now)
string json_out = JsonConvert.SerializeObject(rv, Newtonsoft.Json.Formatting.Indented).Replace("\r\n", "\n");
//ApprovalTests.Approvals.VerifyJson(json_out); --> becomes the code below:
ApprovalTests.Approvals.Verify(
new QiqqaApprover(json_out, pubmed_filepath),
ApprovalTests.Approvals.GetReporter()
);
}