edsl 0.1.39.dev1__py3-none-any.whl → 0.1.39.dev3__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (256) hide show
  1. edsl/Base.py +332 -332
  2. edsl/BaseDiff.py +260 -260
  3. edsl/TemplateLoader.py +24 -24
  4. edsl/__init__.py +49 -49
  5. edsl/__version__.py +1 -1
  6. edsl/agents/Agent.py +867 -867
  7. edsl/agents/AgentList.py +413 -413
  8. edsl/agents/Invigilator.py +233 -233
  9. edsl/agents/InvigilatorBase.py +270 -265
  10. edsl/agents/PromptConstructor.py +354 -354
  11. edsl/agents/__init__.py +3 -3
  12. edsl/agents/descriptors.py +99 -99
  13. edsl/agents/prompt_helpers.py +129 -129
  14. edsl/auto/AutoStudy.py +117 -117
  15. edsl/auto/StageBase.py +230 -230
  16. edsl/auto/StageGenerateSurvey.py +178 -178
  17. edsl/auto/StageLabelQuestions.py +125 -125
  18. edsl/auto/StagePersona.py +61 -61
  19. edsl/auto/StagePersonaDimensionValueRanges.py +88 -88
  20. edsl/auto/StagePersonaDimensionValues.py +74 -74
  21. edsl/auto/StagePersonaDimensions.py +69 -69
  22. edsl/auto/StageQuestions.py +73 -73
  23. edsl/auto/SurveyCreatorPipeline.py +21 -21
  24. edsl/auto/utilities.py +224 -224
  25. edsl/base/Base.py +279 -279
  26. edsl/config.py +157 -157
  27. edsl/conversation/Conversation.py +290 -290
  28. edsl/conversation/car_buying.py +58 -58
  29. edsl/conversation/chips.py +95 -95
  30. edsl/conversation/mug_negotiation.py +81 -81
  31. edsl/conversation/next_speaker_utilities.py +93 -93
  32. edsl/coop/PriceFetcher.py +54 -54
  33. edsl/coop/__init__.py +2 -2
  34. edsl/coop/coop.py +1028 -1028
  35. edsl/coop/utils.py +131 -131
  36. edsl/data/Cache.py +555 -555
  37. edsl/data/CacheEntry.py +233 -233
  38. edsl/data/CacheHandler.py +149 -149
  39. edsl/data/RemoteCacheSync.py +78 -78
  40. edsl/data/SQLiteDict.py +292 -292
  41. edsl/data/__init__.py +4 -4
  42. edsl/data/orm.py +10 -10
  43. edsl/data_transfer_models.py +73 -73
  44. edsl/enums.py +175 -175
  45. edsl/exceptions/BaseException.py +21 -21
  46. edsl/exceptions/__init__.py +54 -54
  47. edsl/exceptions/agents.py +42 -42
  48. edsl/exceptions/cache.py +5 -5
  49. edsl/exceptions/configuration.py +16 -16
  50. edsl/exceptions/coop.py +10 -10
  51. edsl/exceptions/data.py +14 -14
  52. edsl/exceptions/general.py +34 -34
  53. edsl/exceptions/jobs.py +33 -33
  54. edsl/exceptions/language_models.py +63 -63
  55. edsl/exceptions/prompts.py +15 -15
  56. edsl/exceptions/questions.py +91 -91
  57. edsl/exceptions/results.py +29 -29
  58. edsl/exceptions/scenarios.py +22 -22
  59. edsl/exceptions/surveys.py +37 -37
  60. edsl/inference_services/AnthropicService.py +87 -87
  61. edsl/inference_services/AwsBedrock.py +120 -120
  62. edsl/inference_services/AzureAI.py +217 -217
  63. edsl/inference_services/DeepInfraService.py +18 -18
  64. edsl/inference_services/GoogleService.py +148 -148
  65. edsl/inference_services/GroqService.py +20 -20
  66. edsl/inference_services/InferenceServiceABC.py +147 -147
  67. edsl/inference_services/InferenceServicesCollection.py +97 -97
  68. edsl/inference_services/MistralAIService.py +123 -123
  69. edsl/inference_services/OllamaService.py +18 -18
  70. edsl/inference_services/OpenAIService.py +224 -224
  71. edsl/inference_services/PerplexityService.py +163 -163
  72. edsl/inference_services/TestService.py +89 -89
  73. edsl/inference_services/TogetherAIService.py +170 -170
  74. edsl/inference_services/models_available_cache.py +118 -118
  75. edsl/inference_services/rate_limits_cache.py +25 -25
  76. edsl/inference_services/registry.py +41 -41
  77. edsl/inference_services/write_available.py +10 -10
  78. edsl/jobs/Answers.py +56 -56
  79. edsl/jobs/Jobs.py +898 -898
  80. edsl/jobs/JobsChecks.py +147 -147
  81. edsl/jobs/JobsPrompts.py +268 -268
  82. edsl/jobs/JobsRemoteInferenceHandler.py +239 -239
  83. edsl/jobs/__init__.py +1 -1
  84. edsl/jobs/buckets/BucketCollection.py +63 -63
  85. edsl/jobs/buckets/ModelBuckets.py +65 -65
  86. edsl/jobs/buckets/TokenBucket.py +251 -251
  87. edsl/jobs/interviews/Interview.py +661 -661
  88. edsl/jobs/interviews/InterviewExceptionCollection.py +99 -99
  89. edsl/jobs/interviews/InterviewExceptionEntry.py +186 -186
  90. edsl/jobs/interviews/InterviewStatistic.py +63 -63
  91. edsl/jobs/interviews/InterviewStatisticsCollection.py +25 -25
  92. edsl/jobs/interviews/InterviewStatusDictionary.py +78 -78
  93. edsl/jobs/interviews/InterviewStatusLog.py +92 -92
  94. edsl/jobs/interviews/ReportErrors.py +66 -66
  95. edsl/jobs/interviews/interview_status_enum.py +9 -9
  96. edsl/jobs/runners/JobsRunnerAsyncio.py +466 -466
  97. edsl/jobs/runners/JobsRunnerStatus.py +330 -330
  98. edsl/jobs/tasks/QuestionTaskCreator.py +242 -242
  99. edsl/jobs/tasks/TaskCreators.py +64 -64
  100. edsl/jobs/tasks/TaskHistory.py +450 -450
  101. edsl/jobs/tasks/TaskStatusLog.py +23 -23
  102. edsl/jobs/tasks/task_status_enum.py +163 -163
  103. edsl/jobs/tokens/InterviewTokenUsage.py +27 -27
  104. edsl/jobs/tokens/TokenUsage.py +34 -34
  105. edsl/language_models/KeyLookup.py +30 -30
  106. edsl/language_models/LanguageModel.py +668 -668
  107. edsl/language_models/ModelList.py +155 -155
  108. edsl/language_models/RegisterLanguageModelsMeta.py +184 -184
  109. edsl/language_models/__init__.py +3 -3
  110. edsl/language_models/fake_openai_call.py +15 -15
  111. edsl/language_models/fake_openai_service.py +61 -61
  112. edsl/language_models/registry.py +190 -190
  113. edsl/language_models/repair.py +156 -156
  114. edsl/language_models/unused/ReplicateBase.py +83 -83
  115. edsl/language_models/utilities.py +64 -64
  116. edsl/notebooks/Notebook.py +258 -258
  117. edsl/notebooks/__init__.py +1 -1
  118. edsl/prompts/Prompt.py +362 -362
  119. edsl/prompts/__init__.py +2 -2
  120. edsl/questions/AnswerValidatorMixin.py +289 -289
  121. edsl/questions/QuestionBase.py +664 -664
  122. edsl/questions/QuestionBaseGenMixin.py +161 -161
  123. edsl/questions/QuestionBasePromptsMixin.py +217 -217
  124. edsl/questions/QuestionBudget.py +227 -227
  125. edsl/questions/QuestionCheckBox.py +359 -359
  126. edsl/questions/QuestionExtract.py +182 -182
  127. edsl/questions/QuestionFreeText.py +114 -114
  128. edsl/questions/QuestionFunctional.py +166 -166
  129. edsl/questions/QuestionList.py +231 -231
  130. edsl/questions/QuestionMultipleChoice.py +286 -286
  131. edsl/questions/QuestionNumerical.py +153 -153
  132. edsl/questions/QuestionRank.py +324 -324
  133. edsl/questions/Quick.py +41 -41
  134. edsl/questions/RegisterQuestionsMeta.py +71 -71
  135. edsl/questions/ResponseValidatorABC.py +174 -174
  136. edsl/questions/SimpleAskMixin.py +73 -73
  137. edsl/questions/__init__.py +26 -26
  138. edsl/questions/compose_questions.py +98 -98
  139. edsl/questions/decorators.py +21 -21
  140. edsl/questions/derived/QuestionLikertFive.py +76 -76
  141. edsl/questions/derived/QuestionLinearScale.py +87 -87
  142. edsl/questions/derived/QuestionTopK.py +93 -93
  143. edsl/questions/derived/QuestionYesNo.py +82 -82
  144. edsl/questions/descriptors.py +413 -413
  145. edsl/questions/prompt_templates/question_budget.jinja +13 -13
  146. edsl/questions/prompt_templates/question_checkbox.jinja +32 -32
  147. edsl/questions/prompt_templates/question_extract.jinja +11 -11
  148. edsl/questions/prompt_templates/question_free_text.jinja +3 -3
  149. edsl/questions/prompt_templates/question_linear_scale.jinja +11 -11
  150. edsl/questions/prompt_templates/question_list.jinja +17 -17
  151. edsl/questions/prompt_templates/question_multiple_choice.jinja +33 -33
  152. edsl/questions/prompt_templates/question_numerical.jinja +36 -36
  153. edsl/questions/question_registry.py +177 -177
  154. edsl/questions/settings.py +12 -12
  155. edsl/questions/templates/budget/answering_instructions.jinja +7 -7
  156. edsl/questions/templates/budget/question_presentation.jinja +7 -7
  157. edsl/questions/templates/checkbox/answering_instructions.jinja +10 -10
  158. edsl/questions/templates/checkbox/question_presentation.jinja +22 -22
  159. edsl/questions/templates/extract/answering_instructions.jinja +7 -7
  160. edsl/questions/templates/likert_five/answering_instructions.jinja +10 -10
  161. edsl/questions/templates/likert_five/question_presentation.jinja +11 -11
  162. edsl/questions/templates/linear_scale/answering_instructions.jinja +5 -5
  163. edsl/questions/templates/linear_scale/question_presentation.jinja +5 -5
  164. edsl/questions/templates/list/answering_instructions.jinja +3 -3
  165. edsl/questions/templates/list/question_presentation.jinja +5 -5
  166. edsl/questions/templates/multiple_choice/answering_instructions.jinja +9 -9
  167. edsl/questions/templates/multiple_choice/question_presentation.jinja +11 -11
  168. edsl/questions/templates/numerical/answering_instructions.jinja +6 -6
  169. edsl/questions/templates/numerical/question_presentation.jinja +6 -6
  170. edsl/questions/templates/rank/answering_instructions.jinja +11 -11
  171. edsl/questions/templates/rank/question_presentation.jinja +15 -15
  172. edsl/questions/templates/top_k/answering_instructions.jinja +8 -8
  173. edsl/questions/templates/top_k/question_presentation.jinja +22 -22
  174. edsl/questions/templates/yes_no/answering_instructions.jinja +6 -6
  175. edsl/questions/templates/yes_no/question_presentation.jinja +11 -11
  176. edsl/results/CSSParameterizer.py +108 -108
  177. edsl/results/Dataset.py +424 -424
  178. edsl/results/DatasetExportMixin.py +731 -731
  179. edsl/results/DatasetTree.py +275 -275
  180. edsl/results/Result.py +465 -465
  181. edsl/results/Results.py +1165 -1165
  182. edsl/results/ResultsDBMixin.py +238 -238
  183. edsl/results/ResultsExportMixin.py +43 -43
  184. edsl/results/ResultsFetchMixin.py +33 -33
  185. edsl/results/ResultsGGMixin.py +121 -121
  186. edsl/results/ResultsToolsMixin.py +98 -98
  187. edsl/results/Selector.py +135 -135
  188. edsl/results/TableDisplay.py +198 -198
  189. edsl/results/__init__.py +2 -2
  190. edsl/results/table_display.css +77 -77
  191. edsl/results/tree_explore.py +115 -115
  192. edsl/scenarios/FileStore.py +632 -632
  193. edsl/scenarios/Scenario.py +601 -601
  194. edsl/scenarios/ScenarioHtmlMixin.py +64 -64
  195. edsl/scenarios/ScenarioJoin.py +127 -127
  196. edsl/scenarios/ScenarioList.py +1287 -1287
  197. edsl/scenarios/ScenarioListExportMixin.py +52 -52
  198. edsl/scenarios/ScenarioListPdfMixin.py +261 -261
  199. edsl/scenarios/__init__.py +4 -4
  200. edsl/shared.py +1 -1
  201. edsl/study/ObjectEntry.py +173 -173
  202. edsl/study/ProofOfWork.py +113 -113
  203. edsl/study/SnapShot.py +80 -80
  204. edsl/study/Study.py +528 -528
  205. edsl/study/__init__.py +4 -4
  206. edsl/surveys/DAG.py +148 -148
  207. edsl/surveys/Memory.py +31 -31
  208. edsl/surveys/MemoryPlan.py +244 -244
  209. edsl/surveys/Rule.py +326 -326
  210. edsl/surveys/RuleCollection.py +387 -387
  211. edsl/surveys/Survey.py +1801 -1801
  212. edsl/surveys/SurveyCSS.py +261 -261
  213. edsl/surveys/SurveyExportMixin.py +259 -259
  214. edsl/surveys/SurveyFlowVisualizationMixin.py +179 -179
  215. edsl/surveys/SurveyQualtricsImport.py +284 -284
  216. edsl/surveys/__init__.py +3 -3
  217. edsl/surveys/base.py +53 -53
  218. edsl/surveys/descriptors.py +56 -56
  219. edsl/surveys/instructions/ChangeInstruction.py +49 -49
  220. edsl/surveys/instructions/Instruction.py +65 -65
  221. edsl/surveys/instructions/InstructionCollection.py +77 -77
  222. edsl/templates/error_reporting/base.html +23 -23
  223. edsl/templates/error_reporting/exceptions_by_model.html +34 -34
  224. edsl/templates/error_reporting/exceptions_by_question_name.html +16 -16
  225. edsl/templates/error_reporting/exceptions_by_type.html +16 -16
  226. edsl/templates/error_reporting/interview_details.html +115 -115
  227. edsl/templates/error_reporting/interviews.html +19 -19
  228. edsl/templates/error_reporting/overview.html +4 -4
  229. edsl/templates/error_reporting/performance_plot.html +1 -1
  230. edsl/templates/error_reporting/report.css +73 -73
  231. edsl/templates/error_reporting/report.html +117 -117
  232. edsl/templates/error_reporting/report.js +25 -25
  233. edsl/tools/__init__.py +1 -1
  234. edsl/tools/clusters.py +192 -192
  235. edsl/tools/embeddings.py +27 -27
  236. edsl/tools/embeddings_plotting.py +118 -118
  237. edsl/tools/plotting.py +112 -112
  238. edsl/tools/summarize.py +18 -18
  239. edsl/utilities/SystemInfo.py +28 -28
  240. edsl/utilities/__init__.py +22 -22
  241. edsl/utilities/ast_utilities.py +25 -25
  242. edsl/utilities/data/Registry.py +6 -6
  243. edsl/utilities/data/__init__.py +1 -1
  244. edsl/utilities/data/scooter_results.json +1 -1
  245. edsl/utilities/decorators.py +77 -77
  246. edsl/utilities/gcp_bucket/cloud_storage.py +96 -96
  247. edsl/utilities/interface.py +627 -627
  248. edsl/utilities/naming_utilities.py +263 -263
  249. edsl/utilities/repair_functions.py +28 -28
  250. edsl/utilities/restricted_python.py +70 -70
  251. edsl/utilities/utilities.py +424 -424
  252. {edsl-0.1.39.dev1.dist-info → edsl-0.1.39.dev3.dist-info}/LICENSE +21 -21
  253. {edsl-0.1.39.dev1.dist-info → edsl-0.1.39.dev3.dist-info}/METADATA +1 -1
  254. edsl-0.1.39.dev3.dist-info/RECORD +277 -0
  255. edsl-0.1.39.dev1.dist-info/RECORD +0 -277
  256. {edsl-0.1.39.dev1.dist-info → edsl-0.1.39.dev3.dist-info}/WHEEL +0 -0
@@ -1,632 +1,632 @@
1
- import base64
2
- import io
3
- import tempfile
4
- import mimetypes
5
- import os
6
- from typing import Dict, Any, IO, Optional
7
- import requests
8
- from urllib.parse import urlparse
9
-
10
- import google.generativeai as genai
11
-
12
- from edsl import Scenario
13
- from edsl.utilities.decorators import add_edsl_version, remove_edsl_version
14
- from edsl.utilities.utilities import is_notebook
15
-
16
-
17
- def view_csv(csv_path):
18
- import pandas as pd
19
-
20
- df = pd.read_csv(csv_path)
21
- return df
22
-
23
-
24
- def view_html(html_path):
25
- import os
26
- import subprocess
27
- from IPython.display import IFrame, display, HTML
28
-
29
- if os.path.exists(html_path):
30
- if is_notebook():
31
- # Display the HTML inline in Jupyter Notebook
32
- display(IFrame(src=html_path, width=700, height=600))
33
- display(
34
- HTML(
35
- f'<a href="{html_path}" target="_blank">Open HTML in a new tab</a>'
36
- )
37
- )
38
- else:
39
- try:
40
- if (os_name := os.name) == "posix":
41
- # Open with the default browser on macOS
42
- subprocess.run(["open", html_path], check=True)
43
- elif os_name == "nt":
44
- # Open with the default browser on Windows
45
- os.startfile(html_path)
46
- else:
47
- # Open with the default browser on Linux
48
- subprocess.run(["xdg-open", html_path], check=True)
49
- except Exception as e:
50
- print(f"Error opening HTML file: {e}")
51
- else:
52
- print("HTML file was not found.")
53
-
54
-
55
- def view_html(html_path):
56
- import os
57
- from IPython.display import display, HTML
58
-
59
- if is_notebook():
60
- with open(html_path, "r") as f:
61
- html_content = f.read()
62
- display(HTML(html_content))
63
- else:
64
- if os.path.exists(html_path):
65
- try:
66
- if (os_name := os.name) == "posix":
67
- subprocess.run(["open", html_path], check=True)
68
- elif os_name == "nt":
69
- os.startfile(html_path)
70
- else:
71
- subprocess.run(["xdg-open", html_path], check=True)
72
- except Exception as e:
73
- print(f"Error opening file: {e}")
74
- else:
75
- print("File was not created successfully.")
76
-
77
-
78
- def view_pdf(pdf_path):
79
- import os
80
- import subprocess
81
- import os
82
- from IPython.display import HTML, display
83
-
84
- if is_notebook():
85
- # Convert to absolute path if needed
86
- with open(pdf_path, "rb") as f:
87
- base64_pdf = base64.b64encode(f.read()).decode("utf-8")
88
-
89
- html = f"""
90
- <iframe
91
- src="data:application/pdf;base64,{base64_pdf}"
92
- width="800px"
93
- height="800px"
94
- type="application/pdf"
95
- ></iframe>
96
- """
97
- display(HTML(html))
98
-
99
- if os.path.exists(pdf_path):
100
- try:
101
- if (os_name := os.name) == "posix":
102
- # for cool kids
103
- subprocess.run(["open", pdf_path], check=True) # macOS
104
- elif os_name == "nt":
105
- os.startfile(pdf_path) # Windows
106
- else:
107
- subprocess.run(["xdg-open", pdf_path], check=True) # Linux
108
- except Exception as e:
109
- print(f"Error opening PDF: {e}")
110
- else:
111
- print("PDF file was not created successfully.")
112
-
113
-
114
- class FileStore(Scenario):
115
- __documentation__ = "https://docs.expectedparrot.com/en/latest/filestore.html"
116
-
117
- def __init__(
118
- self,
119
- path: Optional[str] = None,
120
- mime_type: Optional[str] = None,
121
- binary: Optional[bool] = None,
122
- suffix: Optional[str] = None,
123
- base64_string: Optional[str] = None,
124
- external_locations: Optional[Dict[str, str]] = None,
125
- **kwargs,
126
- ):
127
- if path is None and "filename" in kwargs:
128
- path = kwargs["filename"]
129
-
130
- self._path = path # Store the original path privately
131
- self._temp_path = None # Track any generated temporary file
132
-
133
- self.suffix = suffix or path.split(".")[-1]
134
- self.binary = binary or False
135
- self.mime_type = (
136
- mime_type or mimetypes.guess_type(path)[0] or "application/octet-stream"
137
- )
138
- self.base64_string = base64_string or self.encode_file_to_base64_string(path)
139
- self.external_locations = external_locations or {}
140
- super().__init__(
141
- {
142
- "path": path,
143
- "base64_string": self.base64_string,
144
- "binary": self.binary,
145
- "suffix": self.suffix,
146
- "mime_type": self.mime_type,
147
- "external_locations": self.external_locations,
148
- }
149
- )
150
-
151
- @property
152
- def path(self) -> str:
153
- """
154
- Property that returns a valid path to the file content.
155
- If the original path doesn't exist, generates a temporary file from the base64 content.
156
- """
157
- # Check if original path exists and is accessible
158
- if self._path and os.path.isfile(self._path):
159
- return self._path
160
-
161
- # If we already have a valid temporary file, use it
162
- if self._temp_path and os.path.isfile(self._temp_path):
163
- return self._temp_path
164
-
165
- # Generate a new temporary file from base64 content
166
- self._temp_path = self.to_tempfile(self.suffix)
167
- return self._temp_path
168
-
169
- def __str__(self):
170
- return "FileStore: self.path"
171
-
172
- @classmethod
173
- def example(cls, example_type="text"):
174
- import textwrap
175
- import tempfile
176
-
177
- if example_type == "png" or example_type == "image":
178
- import importlib.resources
179
- from pathlib import Path
180
-
181
- # Get package root directory
182
- package_root = Path(__file__).parent.parent.parent
183
- logo_path = package_root / "static" / "logo.png"
184
- return cls(str(logo_path))
185
-
186
- if example_type == "text":
187
- with tempfile.NamedTemporaryFile(suffix=".txt", delete=False) as f:
188
- f.write(b"Hello, World!")
189
-
190
- return cls(path=f.name)
191
-
192
- elif example_type == "csv":
193
- from edsl.results.Results import Results
194
-
195
- r = Results.example()
196
-
197
- with tempfile.NamedTemporaryFile(suffix=".csv", delete=False) as f:
198
- r.to_csv(filename=f.name)
199
- return cls(f.name)
200
-
201
- elif example_type == "pdf":
202
- pdf_string = textwrap.dedent(
203
- """\
204
- %PDF-1.4
205
- 1 0 obj
206
- << /Type /Catalog /Pages 2 0 R >>
207
- endobj
208
- 2 0 obj
209
- << /Type /Pages /Kids [3 0 R] /Count 1 >>
210
- endobj
211
- 3 0 obj
212
- << /Type /Page /Parent 2 0 R /MediaBox [0 0 612 792] /Contents 4 0 R >>
213
- endobj
214
- 4 0 obj
215
- << /Length 44 >>
216
- stream
217
- BT
218
- /F1 24 Tf
219
- 100 700 Td
220
- (Hello, World!) Tj
221
- ET
222
- endstream
223
- endobj
224
- 5 0 obj
225
- << /Type /Font /Subtype /Type1 /BaseFont /Helvetica >>
226
- endobj
227
- 6 0 obj
228
- << /ProcSet [/PDF /Text] /Font << /F1 5 0 R >> >>
229
- endobj
230
- xref
231
- 0 7
232
- 0000000000 65535 f
233
- 0000000010 00000 n
234
- 0000000053 00000 n
235
- 0000000100 00000 n
236
- 0000000173 00000 n
237
- 0000000232 00000 n
238
- 0000000272 00000 n
239
- trailer
240
- << /Size 7 /Root 1 0 R >>
241
- startxref
242
- 318
243
- %%EOF"""
244
- )
245
- with tempfile.NamedTemporaryFile(suffix=".pdf", delete=False) as f:
246
- f.write(pdf_string.encode())
247
-
248
- return cls(f.name)
249
-
250
- elif example_type == "html":
251
- with tempfile.NamedTemporaryFile(suffix=".html", delete=False) as f:
252
- f.write("<html><body><h1>Test</h1></body></html>".encode())
253
-
254
- return cls(f.name)
255
-
256
- @property
257
- def size(self) -> int:
258
- if self.base64_string != None:
259
- return (len(self.base64_string) / 4.0) * 3 # from base64 to char size
260
- return os.path.getsize(self.path)
261
-
262
- def upload_google(self, refresh: bool = False) -> None:
263
- genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))
264
- google_info = genai.upload_file(self.path, mime_type=self.mime_type)
265
- self.external_locations["google"] = google_info.to_dict()
266
-
267
- @classmethod
268
- @remove_edsl_version
269
- def from_dict(cls, d):
270
- # return cls(d["filename"], d["binary"], d["suffix"], d["base64_string"])
271
- return cls(**d)
272
-
273
- def __repr__(self):
274
- return f"FileStore(path='{self.path}')"
275
-
276
- def encode_file_to_base64_string(self, file_path: str):
277
- try:
278
- # Attempt to open the file in text mode
279
- with open(file_path, "r") as text_file:
280
- # Read the text data
281
- text_data = text_file.read()
282
- # Encode the text data to a base64 string
283
- base64_encoded_data = base64.b64encode(text_data.encode("utf-8"))
284
- except UnicodeDecodeError:
285
- # If reading as text fails, open the file in binary mode
286
- with open(file_path, "rb") as binary_file:
287
- # Read the binary data
288
- binary_data = binary_file.read()
289
- # Encode the binary data to a base64 string
290
- base64_encoded_data = base64.b64encode(binary_data)
291
- self.binary = True
292
- # Convert the base64 bytes to a string
293
- base64_string = base64_encoded_data.decode("utf-8")
294
-
295
- return base64_string
296
-
297
- def open(self) -> "IO":
298
- if self.binary:
299
- return self.base64_to_file(self["base64_string"], is_binary=True)
300
- else:
301
- return self.base64_to_text_file(self["base64_string"])
302
-
303
- @staticmethod
304
- def base64_to_text_file(base64_string) -> "IO":
305
- # Decode the base64 string to bytes
306
- text_data_bytes = base64.b64decode(base64_string)
307
-
308
- # Convert bytes to string
309
- text_data = text_data_bytes.decode("utf-8")
310
-
311
- # Create a StringIO object from the text data
312
- text_file = io.StringIO(text_data)
313
-
314
- return text_file
315
-
316
- @staticmethod
317
- def base64_to_file(base64_string, is_binary=True):
318
- # Decode the base64 string to bytes
319
- file_data = base64.b64decode(base64_string)
320
-
321
- if is_binary:
322
- # Create a BytesIO object for binary data
323
- return io.BytesIO(file_data)
324
- else:
325
- # Convert bytes to string for text data
326
- text_data = file_data.decode("utf-8")
327
- # Create a StringIO object for text data
328
- return io.StringIO(text_data)
329
-
330
- def to_tempfile(self, suffix=None):
331
- if suffix is None:
332
- suffix = self.suffix
333
- if self.binary:
334
- file_like_object = self.base64_to_file(
335
- self["base64_string"], is_binary=True
336
- )
337
- else:
338
- file_like_object = self.base64_to_text_file(self["base64_string"])
339
-
340
- # Create a named temporary file
341
- mode = "wb" if self.binary else "w"
342
- temp_file = tempfile.NamedTemporaryFile(
343
- delete=False, suffix="." + suffix, mode=mode
344
- )
345
-
346
- if self.binary:
347
- temp_file.write(file_like_object.read())
348
- else:
349
- temp_file.write(file_like_object.read())
350
-
351
- temp_file.close()
352
-
353
- return temp_file.name
354
-
355
- def view(self, max_size: int = 300) -> None:
356
- # with self.open() as f:
357
- if self.suffix == "csv":
358
- return view_csv(self.path)
359
-
360
- if self.suffix == "pdf":
361
- view_pdf(self.path)
362
-
363
- if self.suffix == "html":
364
- view_html(self.path)
365
-
366
- if self.suffix == "png" or self.suffix == "jpg" or self.suffix == "jpeg":
367
- if is_notebook():
368
- from IPython.display import Image
369
- from PIL import Image as PILImage
370
-
371
- if max_size:
372
- # Open the image using Pillow
373
- with PILImage.open(self.path) as img:
374
- # Get original width and height
375
- original_width, original_height = img.size
376
-
377
- # Calculate the scaling factor
378
- scale = min(
379
- max_size / original_width, max_size / original_height
380
- )
381
-
382
- # Calculate new dimensions
383
- new_width = int(original_width * scale)
384
- new_height = int(original_height * scale)
385
-
386
- return Image(self.path, width=new_width, height=new_height)
387
- else:
388
- return Image(self.path)
389
-
390
- def push(
391
- self, description: Optional[str] = None, visibility: str = "unlisted"
392
- ) -> dict:
393
- """
394
- Push the object to Coop.
395
- :param description: The description of the object to push.
396
- :param visibility: The visibility of the object to push.
397
- """
398
- scenario_version = Scenario.from_dict(self.to_dict())
399
- if description is None:
400
- description = "File: " + self.path
401
- info = scenario_version.push(description=description, visibility=visibility)
402
- return info
403
-
404
- @classmethod
405
- def pull(cls, uuid: str, expected_parrot_url: Optional[str] = None) -> "FileStore":
406
- """
407
- :param uuid: The UUID of the object to pull.
408
- :param expected_parrot_url: The URL of the Parrot server to use.
409
- :return: The object pulled from the Parrot server.
410
- """
411
- scenario_version = Scenario.pull(uuid, expected_parrot_url=expected_parrot_url)
412
- return cls.from_dict(scenario_version.to_dict())
413
-
414
- @classmethod
415
- def from_url(
416
- cls,
417
- url: str,
418
- download_path: Optional[str] = None,
419
- mime_type: Optional[str] = None,
420
- ) -> "FileStore":
421
- """
422
- :param url: The URL of the file to download.
423
- :param download_path: The path to save the downloaded file.
424
- :param mime_type: The MIME type of the file. If None, it will be guessed from the file extension.
425
- """
426
-
427
- response = requests.get(url, stream=True)
428
- response.raise_for_status() # Raises an HTTPError for bad responses
429
-
430
- # Get the filename from the URL if download_path is not provided
431
- if download_path is None:
432
- filename = os.path.basename(urlparse(url).path)
433
- if not filename:
434
- filename = "downloaded_file"
435
- # download_path = filename
436
- download_path = os.path.join(os.getcwd(), filename)
437
-
438
- # Ensure the directory exists
439
- os.makedirs(os.path.dirname(download_path), exist_ok=True)
440
-
441
- # Write the file
442
- with open(download_path, "wb") as file:
443
- for chunk in response.iter_content(chunk_size=8192):
444
- file.write(chunk)
445
-
446
- # Create and return a new File instance
447
- return cls(download_path, mime_type=mime_type)
448
-
449
-
450
- class CSVFileStore(FileStore):
451
- @classmethod
452
- def example(cls):
453
- from edsl.results.Results import Results
454
-
455
- r = Results.example()
456
- import tempfile
457
-
458
- with tempfile.NamedTemporaryFile(suffix=".csv", delete=False) as f:
459
- r.to_csv(filename=f.name)
460
-
461
- return cls(f.name)
462
-
463
- def view(self):
464
- import pandas as pd
465
-
466
- return pd.read_csv(self.to_tempfile())
467
-
468
-
469
- class PDFFileStore(FileStore):
470
- def view(self):
471
- pdf_path = self.to_tempfile()
472
- print(f"PDF path: {pdf_path}") # Print the path to ensure it exists
473
- import os
474
- import subprocess
475
-
476
- if os.path.exists(pdf_path):
477
- try:
478
- if os.name == "posix":
479
- # for cool kids
480
- subprocess.run(["open", pdf_path], check=True) # macOS
481
- elif os.name == "nt":
482
- os.startfile(pdf_path) # Windows
483
- else:
484
- subprocess.run(["xdg-open", pdf_path], check=True) # Linux
485
- except Exception as e:
486
- print(f"Error opening PDF: {e}")
487
- else:
488
- print("PDF file was not created successfully.")
489
-
490
- @classmethod
491
- def example(cls):
492
- import textwrap
493
-
494
- pdf_string = textwrap.dedent(
495
- """\
496
- %PDF-1.4
497
- 1 0 obj
498
- << /Type /Catalog /Pages 2 0 R >>
499
- endobj
500
- 2 0 obj
501
- << /Type /Pages /Kids [3 0 R] /Count 1 >>
502
- endobj
503
- 3 0 obj
504
- << /Type /Page /Parent 2 0 R /MediaBox [0 0 612 792] /Contents 4 0 R >>
505
- endobj
506
- 4 0 obj
507
- << /Length 44 >>
508
- stream
509
- BT
510
- /F1 24 Tf
511
- 100 700 Td
512
- (Hello, World!) Tj
513
- ET
514
- endstream
515
- endobj
516
- 5 0 obj
517
- << /Type /Font /Subtype /Type1 /BaseFont /Helvetica >>
518
- endobj
519
- 6 0 obj
520
- << /ProcSet [/PDF /Text] /Font << /F1 5 0 R >> >>
521
- endobj
522
- xref
523
- 0 7
524
- 0000000000 65535 f
525
- 0000000010 00000 n
526
- 0000000053 00000 n
527
- 0000000100 00000 n
528
- 0000000173 00000 n
529
- 0000000232 00000 n
530
- 0000000272 00000 n
531
- trailer
532
- << /Size 7 /Root 1 0 R >>
533
- startxref
534
- 318
535
- %%EOF"""
536
- )
537
- import tempfile
538
-
539
- with tempfile.NamedTemporaryFile(suffix=".pdf", delete=False) as f:
540
- f.write(pdf_string.encode())
541
-
542
- return cls(f.name)
543
-
544
-
545
- class PNGFileStore(FileStore):
546
- @classmethod
547
- def example(cls):
548
- import textwrap
549
-
550
- png_string = textwrap.dedent(
551
- """\x89PNG\r\n\x1a\n\x00\x00\x00\rIHDR\x00\x00\x01\x00\x00\x00\x01\x00\x08\x06\x00\x00\x00\x1f\x15\xc4\x89\x00\x00\x00\x0cIDAT\x08\xd7c\x00\x01"""
552
- )
553
- import tempfile
554
-
555
- with tempfile.NamedTemporaryFile(suffix=".png", delete=False) as f:
556
- f.write(png_string.encode())
557
-
558
- return cls(f.name)
559
-
560
- def view(self):
561
- import matplotlib.pyplot as plt
562
- import matplotlib.image as mpimg
563
-
564
- img = mpimg.imread(self.to_tempfile())
565
- plt.imshow(img)
566
- plt.show()
567
-
568
-
569
- class SQLiteFileStore(FileStore):
570
- @classmethod
571
- def example(cls):
572
- import sqlite3
573
- import tempfile
574
-
575
- with tempfile.NamedTemporaryFile(suffix=".sqlite", delete=False) as f:
576
- conn = sqlite3.connect(f.name)
577
- c = conn.cursor()
578
- c.execute("""CREATE TABLE stocks (date text)""")
579
- conn.commit()
580
-
581
- return cls(f.name)
582
-
583
- def view(self):
584
- import subprocess
585
- import os
586
-
587
- sqlite_path = self.to_tempfile()
588
- os.system(f"sqlite3 {sqlite_path}")
589
-
590
-
591
- class HTMLFileStore(FileStore):
592
- @classmethod
593
- def example(cls):
594
- import tempfile
595
-
596
- with tempfile.NamedTemporaryFile(suffix=".html", delete=False) as f:
597
- f.write("<html><body><h1>Test</h1></body></html>".encode())
598
-
599
- return cls(f.name)
600
-
601
- def view(self):
602
- import webbrowser
603
-
604
- html_path = self.to_tempfile()
605
- webbrowser.open("file://" + html_path)
606
-
607
-
608
- if __name__ == "__main__":
609
- # file_path = "../conjure/examples/Ex11-2.sav"
610
- # fs = FileStore(file_path)
611
- # info = fs.push()
612
- # print(info)
613
-
614
- # fs = CSVFileStore.example()
615
- # fs.to_tempfile()
616
- # print(fs.view())
617
-
618
- # fs = PDFFileStore.example()
619
- # fs.view()
620
-
621
- # fs = PDFFileStore("paper.pdf")
622
- # fs.view()
623
- # from edsl import Conjure
624
- pass
625
- # fs = PNGFileStore("logo.png")
626
- # fs.view()
627
- # fs.upload_google()
628
-
629
- # c = Conjure(datafile_name=fs.to_tempfile())
630
- # f = PDFFileStore("paper.pdf")
631
- # print(f.to_tempfile())
632
- # f.push()
1
+ import base64
2
+ import io
3
+ import tempfile
4
+ import mimetypes
5
+ import os
6
+ from typing import Dict, Any, IO, Optional
7
+ import requests
8
+ from urllib.parse import urlparse
9
+
10
+ import google.generativeai as genai
11
+
12
+ from edsl import Scenario
13
+ from edsl.utilities.decorators import add_edsl_version, remove_edsl_version
14
+ from edsl.utilities.utilities import is_notebook
15
+
16
+
17
+ def view_csv(csv_path):
18
+ import pandas as pd
19
+
20
+ df = pd.read_csv(csv_path)
21
+ return df
22
+
23
+
24
+ def view_html(html_path):
25
+ import os
26
+ import subprocess
27
+ from IPython.display import IFrame, display, HTML
28
+
29
+ if os.path.exists(html_path):
30
+ if is_notebook():
31
+ # Display the HTML inline in Jupyter Notebook
32
+ display(IFrame(src=html_path, width=700, height=600))
33
+ display(
34
+ HTML(
35
+ f'<a href="{html_path}" target="_blank">Open HTML in a new tab</a>'
36
+ )
37
+ )
38
+ else:
39
+ try:
40
+ if (os_name := os.name) == "posix":
41
+ # Open with the default browser on macOS
42
+ subprocess.run(["open", html_path], check=True)
43
+ elif os_name == "nt":
44
+ # Open with the default browser on Windows
45
+ os.startfile(html_path)
46
+ else:
47
+ # Open with the default browser on Linux
48
+ subprocess.run(["xdg-open", html_path], check=True)
49
+ except Exception as e:
50
+ print(f"Error opening HTML file: {e}")
51
+ else:
52
+ print("HTML file was not found.")
53
+
54
+
55
+ def view_html(html_path):
56
+ import os
57
+ from IPython.display import display, HTML
58
+
59
+ if is_notebook():
60
+ with open(html_path, "r") as f:
61
+ html_content = f.read()
62
+ display(HTML(html_content))
63
+ else:
64
+ if os.path.exists(html_path):
65
+ try:
66
+ if (os_name := os.name) == "posix":
67
+ subprocess.run(["open", html_path], check=True)
68
+ elif os_name == "nt":
69
+ os.startfile(html_path)
70
+ else:
71
+ subprocess.run(["xdg-open", html_path], check=True)
72
+ except Exception as e:
73
+ print(f"Error opening file: {e}")
74
+ else:
75
+ print("File was not created successfully.")
76
+
77
+
78
+ def view_pdf(pdf_path):
79
+ import os
80
+ import subprocess
81
+ import os
82
+ from IPython.display import HTML, display
83
+
84
+ if is_notebook():
85
+ # Convert to absolute path if needed
86
+ with open(pdf_path, "rb") as f:
87
+ base64_pdf = base64.b64encode(f.read()).decode("utf-8")
88
+
89
+ html = f"""
90
+ <iframe
91
+ src="data:application/pdf;base64,{base64_pdf}"
92
+ width="800px"
93
+ height="800px"
94
+ type="application/pdf"
95
+ ></iframe>
96
+ """
97
+ display(HTML(html))
98
+
99
+ if os.path.exists(pdf_path):
100
+ try:
101
+ if (os_name := os.name) == "posix":
102
+ # for cool kids
103
+ subprocess.run(["open", pdf_path], check=True) # macOS
104
+ elif os_name == "nt":
105
+ os.startfile(pdf_path) # Windows
106
+ else:
107
+ subprocess.run(["xdg-open", pdf_path], check=True) # Linux
108
+ except Exception as e:
109
+ print(f"Error opening PDF: {e}")
110
+ else:
111
+ print("PDF file was not created successfully.")
112
+
113
+
114
+ class FileStore(Scenario):
115
+ __documentation__ = "https://docs.expectedparrot.com/en/latest/filestore.html"
116
+
117
+ def __init__(
118
+ self,
119
+ path: Optional[str] = None,
120
+ mime_type: Optional[str] = None,
121
+ binary: Optional[bool] = None,
122
+ suffix: Optional[str] = None,
123
+ base64_string: Optional[str] = None,
124
+ external_locations: Optional[Dict[str, str]] = None,
125
+ **kwargs,
126
+ ):
127
+ if path is None and "filename" in kwargs:
128
+ path = kwargs["filename"]
129
+
130
+ self._path = path # Store the original path privately
131
+ self._temp_path = None # Track any generated temporary file
132
+
133
+ self.suffix = suffix or path.split(".")[-1]
134
+ self.binary = binary or False
135
+ self.mime_type = (
136
+ mime_type or mimetypes.guess_type(path)[0] or "application/octet-stream"
137
+ )
138
+ self.base64_string = base64_string or self.encode_file_to_base64_string(path)
139
+ self.external_locations = external_locations or {}
140
+ super().__init__(
141
+ {
142
+ "path": path,
143
+ "base64_string": self.base64_string,
144
+ "binary": self.binary,
145
+ "suffix": self.suffix,
146
+ "mime_type": self.mime_type,
147
+ "external_locations": self.external_locations,
148
+ }
149
+ )
150
+
151
+ @property
152
+ def path(self) -> str:
153
+ """
154
+ Property that returns a valid path to the file content.
155
+ If the original path doesn't exist, generates a temporary file from the base64 content.
156
+ """
157
+ # Check if original path exists and is accessible
158
+ if self._path and os.path.isfile(self._path):
159
+ return self._path
160
+
161
+ # If we already have a valid temporary file, use it
162
+ if self._temp_path and os.path.isfile(self._temp_path):
163
+ return self._temp_path
164
+
165
+ # Generate a new temporary file from base64 content
166
+ self._temp_path = self.to_tempfile(self.suffix)
167
+ return self._temp_path
168
+
169
+ def __str__(self):
170
+ return "FileStore: self.path"
171
+
172
+ @classmethod
173
+ def example(cls, example_type="text"):
174
+ import textwrap
175
+ import tempfile
176
+
177
+ if example_type == "png" or example_type == "image":
178
+ import importlib.resources
179
+ from pathlib import Path
180
+
181
+ # Get package root directory
182
+ package_root = Path(__file__).parent.parent.parent
183
+ logo_path = package_root / "static" / "logo.png"
184
+ return cls(str(logo_path))
185
+
186
+ if example_type == "text":
187
+ with tempfile.NamedTemporaryFile(suffix=".txt", delete=False) as f:
188
+ f.write(b"Hello, World!")
189
+
190
+ return cls(path=f.name)
191
+
192
+ elif example_type == "csv":
193
+ from edsl.results.Results import Results
194
+
195
+ r = Results.example()
196
+
197
+ with tempfile.NamedTemporaryFile(suffix=".csv", delete=False) as f:
198
+ r.to_csv(filename=f.name)
199
+ return cls(f.name)
200
+
201
+ elif example_type == "pdf":
202
+ pdf_string = textwrap.dedent(
203
+ """\
204
+ %PDF-1.4
205
+ 1 0 obj
206
+ << /Type /Catalog /Pages 2 0 R >>
207
+ endobj
208
+ 2 0 obj
209
+ << /Type /Pages /Kids [3 0 R] /Count 1 >>
210
+ endobj
211
+ 3 0 obj
212
+ << /Type /Page /Parent 2 0 R /MediaBox [0 0 612 792] /Contents 4 0 R >>
213
+ endobj
214
+ 4 0 obj
215
+ << /Length 44 >>
216
+ stream
217
+ BT
218
+ /F1 24 Tf
219
+ 100 700 Td
220
+ (Hello, World!) Tj
221
+ ET
222
+ endstream
223
+ endobj
224
+ 5 0 obj
225
+ << /Type /Font /Subtype /Type1 /BaseFont /Helvetica >>
226
+ endobj
227
+ 6 0 obj
228
+ << /ProcSet [/PDF /Text] /Font << /F1 5 0 R >> >>
229
+ endobj
230
+ xref
231
+ 0 7
232
+ 0000000000 65535 f
233
+ 0000000010 00000 n
234
+ 0000000053 00000 n
235
+ 0000000100 00000 n
236
+ 0000000173 00000 n
237
+ 0000000232 00000 n
238
+ 0000000272 00000 n
239
+ trailer
240
+ << /Size 7 /Root 1 0 R >>
241
+ startxref
242
+ 318
243
+ %%EOF"""
244
+ )
245
+ with tempfile.NamedTemporaryFile(suffix=".pdf", delete=False) as f:
246
+ f.write(pdf_string.encode())
247
+
248
+ return cls(f.name)
249
+
250
+ elif example_type == "html":
251
+ with tempfile.NamedTemporaryFile(suffix=".html", delete=False) as f:
252
+ f.write("<html><body><h1>Test</h1></body></html>".encode())
253
+
254
+ return cls(f.name)
255
+
256
+ @property
257
+ def size(self) -> int:
258
+ if self.base64_string != None:
259
+ return (len(self.base64_string) / 4.0) * 3 # from base64 to char size
260
+ return os.path.getsize(self.path)
261
+
262
+ def upload_google(self, refresh: bool = False) -> None:
263
+ genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))
264
+ google_info = genai.upload_file(self.path, mime_type=self.mime_type)
265
+ self.external_locations["google"] = google_info.to_dict()
266
+
267
+ @classmethod
268
+ @remove_edsl_version
269
+ def from_dict(cls, d):
270
+ # return cls(d["filename"], d["binary"], d["suffix"], d["base64_string"])
271
+ return cls(**d)
272
+
273
+ def __repr__(self):
274
+ return f"FileStore(path='{self.path}')"
275
+
276
+ def encode_file_to_base64_string(self, file_path: str):
277
+ try:
278
+ # Attempt to open the file in text mode
279
+ with open(file_path, "r") as text_file:
280
+ # Read the text data
281
+ text_data = text_file.read()
282
+ # Encode the text data to a base64 string
283
+ base64_encoded_data = base64.b64encode(text_data.encode("utf-8"))
284
+ except UnicodeDecodeError:
285
+ # If reading as text fails, open the file in binary mode
286
+ with open(file_path, "rb") as binary_file:
287
+ # Read the binary data
288
+ binary_data = binary_file.read()
289
+ # Encode the binary data to a base64 string
290
+ base64_encoded_data = base64.b64encode(binary_data)
291
+ self.binary = True
292
+ # Convert the base64 bytes to a string
293
+ base64_string = base64_encoded_data.decode("utf-8")
294
+
295
+ return base64_string
296
+
297
+ def open(self) -> "IO":
298
+ if self.binary:
299
+ return self.base64_to_file(self["base64_string"], is_binary=True)
300
+ else:
301
+ return self.base64_to_text_file(self["base64_string"])
302
+
303
+ @staticmethod
304
+ def base64_to_text_file(base64_string) -> "IO":
305
+ # Decode the base64 string to bytes
306
+ text_data_bytes = base64.b64decode(base64_string)
307
+
308
+ # Convert bytes to string
309
+ text_data = text_data_bytes.decode("utf-8")
310
+
311
+ # Create a StringIO object from the text data
312
+ text_file = io.StringIO(text_data)
313
+
314
+ return text_file
315
+
316
+ @staticmethod
317
+ def base64_to_file(base64_string, is_binary=True):
318
+ # Decode the base64 string to bytes
319
+ file_data = base64.b64decode(base64_string)
320
+
321
+ if is_binary:
322
+ # Create a BytesIO object for binary data
323
+ return io.BytesIO(file_data)
324
+ else:
325
+ # Convert bytes to string for text data
326
+ text_data = file_data.decode("utf-8")
327
+ # Create a StringIO object for text data
328
+ return io.StringIO(text_data)
329
+
330
+ def to_tempfile(self, suffix=None):
331
+ if suffix is None:
332
+ suffix = self.suffix
333
+ if self.binary:
334
+ file_like_object = self.base64_to_file(
335
+ self["base64_string"], is_binary=True
336
+ )
337
+ else:
338
+ file_like_object = self.base64_to_text_file(self["base64_string"])
339
+
340
+ # Create a named temporary file
341
+ mode = "wb" if self.binary else "w"
342
+ temp_file = tempfile.NamedTemporaryFile(
343
+ delete=False, suffix="." + suffix, mode=mode
344
+ )
345
+
346
+ if self.binary:
347
+ temp_file.write(file_like_object.read())
348
+ else:
349
+ temp_file.write(file_like_object.read())
350
+
351
+ temp_file.close()
352
+
353
+ return temp_file.name
354
+
355
+ def view(self, max_size: int = 300) -> None:
356
+ # with self.open() as f:
357
+ if self.suffix == "csv":
358
+ return view_csv(self.path)
359
+
360
+ if self.suffix == "pdf":
361
+ view_pdf(self.path)
362
+
363
+ if self.suffix == "html":
364
+ view_html(self.path)
365
+
366
+ if self.suffix == "png" or self.suffix == "jpg" or self.suffix == "jpeg":
367
+ if is_notebook():
368
+ from IPython.display import Image
369
+ from PIL import Image as PILImage
370
+
371
+ if max_size:
372
+ # Open the image using Pillow
373
+ with PILImage.open(self.path) as img:
374
+ # Get original width and height
375
+ original_width, original_height = img.size
376
+
377
+ # Calculate the scaling factor
378
+ scale = min(
379
+ max_size / original_width, max_size / original_height
380
+ )
381
+
382
+ # Calculate new dimensions
383
+ new_width = int(original_width * scale)
384
+ new_height = int(original_height * scale)
385
+
386
+ return Image(self.path, width=new_width, height=new_height)
387
+ else:
388
+ return Image(self.path)
389
+
390
+ def push(
391
+ self, description: Optional[str] = None, visibility: str = "unlisted"
392
+ ) -> dict:
393
+ """
394
+ Push the object to Coop.
395
+ :param description: The description of the object to push.
396
+ :param visibility: The visibility of the object to push.
397
+ """
398
+ scenario_version = Scenario.from_dict(self.to_dict())
399
+ if description is None:
400
+ description = "File: " + self.path
401
+ info = scenario_version.push(description=description, visibility=visibility)
402
+ return info
403
+
404
+ @classmethod
405
+ def pull(cls, uuid: str, expected_parrot_url: Optional[str] = None) -> "FileStore":
406
+ """
407
+ :param uuid: The UUID of the object to pull.
408
+ :param expected_parrot_url: The URL of the Parrot server to use.
409
+ :return: The object pulled from the Parrot server.
410
+ """
411
+ scenario_version = Scenario.pull(uuid, expected_parrot_url=expected_parrot_url)
412
+ return cls.from_dict(scenario_version.to_dict())
413
+
414
+ @classmethod
415
+ def from_url(
416
+ cls,
417
+ url: str,
418
+ download_path: Optional[str] = None,
419
+ mime_type: Optional[str] = None,
420
+ ) -> "FileStore":
421
+ """
422
+ :param url: The URL of the file to download.
423
+ :param download_path: The path to save the downloaded file.
424
+ :param mime_type: The MIME type of the file. If None, it will be guessed from the file extension.
425
+ """
426
+
427
+ response = requests.get(url, stream=True)
428
+ response.raise_for_status() # Raises an HTTPError for bad responses
429
+
430
+ # Get the filename from the URL if download_path is not provided
431
+ if download_path is None:
432
+ filename = os.path.basename(urlparse(url).path)
433
+ if not filename:
434
+ filename = "downloaded_file"
435
+ # download_path = filename
436
+ download_path = os.path.join(os.getcwd(), filename)
437
+
438
+ # Ensure the directory exists
439
+ os.makedirs(os.path.dirname(download_path), exist_ok=True)
440
+
441
+ # Write the file
442
+ with open(download_path, "wb") as file:
443
+ for chunk in response.iter_content(chunk_size=8192):
444
+ file.write(chunk)
445
+
446
+ # Create and return a new File instance
447
+ return cls(download_path, mime_type=mime_type)
448
+
449
+
450
+ class CSVFileStore(FileStore):
451
+ @classmethod
452
+ def example(cls):
453
+ from edsl.results.Results import Results
454
+
455
+ r = Results.example()
456
+ import tempfile
457
+
458
+ with tempfile.NamedTemporaryFile(suffix=".csv", delete=False) as f:
459
+ r.to_csv(filename=f.name)
460
+
461
+ return cls(f.name)
462
+
463
+ def view(self):
464
+ import pandas as pd
465
+
466
+ return pd.read_csv(self.to_tempfile())
467
+
468
+
469
+ class PDFFileStore(FileStore):
470
+ def view(self):
471
+ pdf_path = self.to_tempfile()
472
+ print(f"PDF path: {pdf_path}") # Print the path to ensure it exists
473
+ import os
474
+ import subprocess
475
+
476
+ if os.path.exists(pdf_path):
477
+ try:
478
+ if os.name == "posix":
479
+ # for cool kids
480
+ subprocess.run(["open", pdf_path], check=True) # macOS
481
+ elif os.name == "nt":
482
+ os.startfile(pdf_path) # Windows
483
+ else:
484
+ subprocess.run(["xdg-open", pdf_path], check=True) # Linux
485
+ except Exception as e:
486
+ print(f"Error opening PDF: {e}")
487
+ else:
488
+ print("PDF file was not created successfully.")
489
+
490
+ @classmethod
491
+ def example(cls):
492
+ import textwrap
493
+
494
+ pdf_string = textwrap.dedent(
495
+ """\
496
+ %PDF-1.4
497
+ 1 0 obj
498
+ << /Type /Catalog /Pages 2 0 R >>
499
+ endobj
500
+ 2 0 obj
501
+ << /Type /Pages /Kids [3 0 R] /Count 1 >>
502
+ endobj
503
+ 3 0 obj
504
+ << /Type /Page /Parent 2 0 R /MediaBox [0 0 612 792] /Contents 4 0 R >>
505
+ endobj
506
+ 4 0 obj
507
+ << /Length 44 >>
508
+ stream
509
+ BT
510
+ /F1 24 Tf
511
+ 100 700 Td
512
+ (Hello, World!) Tj
513
+ ET
514
+ endstream
515
+ endobj
516
+ 5 0 obj
517
+ << /Type /Font /Subtype /Type1 /BaseFont /Helvetica >>
518
+ endobj
519
+ 6 0 obj
520
+ << /ProcSet [/PDF /Text] /Font << /F1 5 0 R >> >>
521
+ endobj
522
+ xref
523
+ 0 7
524
+ 0000000000 65535 f
525
+ 0000000010 00000 n
526
+ 0000000053 00000 n
527
+ 0000000100 00000 n
528
+ 0000000173 00000 n
529
+ 0000000232 00000 n
530
+ 0000000272 00000 n
531
+ trailer
532
+ << /Size 7 /Root 1 0 R >>
533
+ startxref
534
+ 318
535
+ %%EOF"""
536
+ )
537
+ import tempfile
538
+
539
+ with tempfile.NamedTemporaryFile(suffix=".pdf", delete=False) as f:
540
+ f.write(pdf_string.encode())
541
+
542
+ return cls(f.name)
543
+
544
+
545
+ class PNGFileStore(FileStore):
546
+ @classmethod
547
+ def example(cls):
548
+ import textwrap
549
+
550
+ png_string = textwrap.dedent(
551
+ """\x89PNG\r\n\x1a\n\x00\x00\x00\rIHDR\x00\x00\x01\x00\x00\x00\x01\x00\x08\x06\x00\x00\x00\x1f\x15\xc4\x89\x00\x00\x00\x0cIDAT\x08\xd7c\x00\x01"""
552
+ )
553
+ import tempfile
554
+
555
+ with tempfile.NamedTemporaryFile(suffix=".png", delete=False) as f:
556
+ f.write(png_string.encode())
557
+
558
+ return cls(f.name)
559
+
560
+ def view(self):
561
+ import matplotlib.pyplot as plt
562
+ import matplotlib.image as mpimg
563
+
564
+ img = mpimg.imread(self.to_tempfile())
565
+ plt.imshow(img)
566
+ plt.show()
567
+
568
+
569
+ class SQLiteFileStore(FileStore):
570
+ @classmethod
571
+ def example(cls):
572
+ import sqlite3
573
+ import tempfile
574
+
575
+ with tempfile.NamedTemporaryFile(suffix=".sqlite", delete=False) as f:
576
+ conn = sqlite3.connect(f.name)
577
+ c = conn.cursor()
578
+ c.execute("""CREATE TABLE stocks (date text)""")
579
+ conn.commit()
580
+
581
+ return cls(f.name)
582
+
583
+ def view(self):
584
+ import subprocess
585
+ import os
586
+
587
+ sqlite_path = self.to_tempfile()
588
+ os.system(f"sqlite3 {sqlite_path}")
589
+
590
+
591
+ class HTMLFileStore(FileStore):
592
+ @classmethod
593
+ def example(cls):
594
+ import tempfile
595
+
596
+ with tempfile.NamedTemporaryFile(suffix=".html", delete=False) as f:
597
+ f.write("<html><body><h1>Test</h1></body></html>".encode())
598
+
599
+ return cls(f.name)
600
+
601
+ def view(self):
602
+ import webbrowser
603
+
604
+ html_path = self.to_tempfile()
605
+ webbrowser.open("file://" + html_path)
606
+
607
+
608
+ if __name__ == "__main__":
609
+ # file_path = "../conjure/examples/Ex11-2.sav"
610
+ # fs = FileStore(file_path)
611
+ # info = fs.push()
612
+ # print(info)
613
+
614
+ # fs = CSVFileStore.example()
615
+ # fs.to_tempfile()
616
+ # print(fs.view())
617
+
618
+ # fs = PDFFileStore.example()
619
+ # fs.view()
620
+
621
+ # fs = PDFFileStore("paper.pdf")
622
+ # fs.view()
623
+ # from edsl import Conjure
624
+ pass
625
+ # fs = PNGFileStore("logo.png")
626
+ # fs.view()
627
+ # fs.upload_google()
628
+
629
+ # c = Conjure(datafile_name=fs.to_tempfile())
630
+ # f = PDFFileStore("paper.pdf")
631
+ # print(f.to_tempfile())
632
+ # f.push()